├── .gitignore ├── texture_nets ├── pollock.t7 ├── starry.t7 ├── README.md ├── NoiseFill.lua ├── stylization.lua └── SpatialCircularPadding.lua ├── neuraltalk2 └── README.md ├── imagenet_classification ├── demo.lua └── synset.t7 ├── face_recognition ├── README.md └── demo.lua ├── README.md └── age_gender └── demo.lua /.gitignore: -------------------------------------------------------------------------------- 1 | *.t7 2 | *.caffemodel 3 | *.prototxt 4 | *.prototxt.lua 5 | *.jpg 6 | -------------------------------------------------------------------------------- /texture_nets/pollock.t7: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/szagoruyko/torch-opencv-demos/HEAD/texture_nets/pollock.t7 -------------------------------------------------------------------------------- /texture_nets/starry.t7: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/szagoruyko/torch-opencv-demos/HEAD/texture_nets/starry.t7 -------------------------------------------------------------------------------- /neuraltalk2/README.md: -------------------------------------------------------------------------------- 1 | NeuralTalk2 demo 2 | ================ 3 | 4 | This demo uses NeuralTalk2 captioning code from Andrej Karpathy: https://github.com/karpathy/neuraltalk2 5 | 6 | The code captions live webcam demo. Follow the installation instructions at 7 | https://github.com/karpathy/neuraltalk2 first and then run the demo as: 8 | 9 | ``` 10 | th videocaptioning.lua -gpuid -1 -model model_id1-501-1448236541_cpu.t7 11 | ``` 12 | -------------------------------------------------------------------------------- /texture_nets/README.md: -------------------------------------------------------------------------------- 1 | Realtime texture_nets 2 | ================ 3 | 4 | This enables realtime stylization with texture networks, for more information check https://github.com/DmitryUlyanov/texture_nets 5 | 6 | For now 'starry night' and 'pollock' models are available, we will add more in future. 7 | 8 | ![screen shot 2016-04-25 at 00 08 15](https://cloud.githubusercontent.com/assets/4953728/14781476/fa8a7c1a-0ae2-11e6-88fb-10e2bf418d86.png) 9 | 10 | # Usage 11 | 12 | The demo depends on folding Batch Normalization into convolution in [imagine-nn](https://github.com/szagoruyko/imagine-nn), to install it do: 13 | 14 | ``` 15 | luarocks install inn 16 | ``` 17 | 18 | To run on CPU do: 19 | 20 | ``` 21 | OMP_NUM_THREADS=2 th stylization.lua 22 | ``` 23 | 24 | On my dual core macbook it takes about ~0.6s to process one frame. 25 | 26 | To run on CUDA do: 27 | 28 | ``` 29 | type=cuda th stylization.lua 30 | ``` 31 | 32 | OpenCL is supported to with `type=cl`. Might be slower than CPU though. 33 | 34 | To run on input video file do: 35 | 36 | ``` 37 | video_path=*path to file* th stylization.lua 38 | ``` 39 | 40 | # Model 41 | 42 | ![outfile](https://cloud.githubusercontent.com/assets/4953728/14781485/02f31ad8-0ae3-11e6-9cdc-8660c34384b3.png) 43 | 44 | # Credits 45 | 46 | Thanks to Dmitry Ulyanov for providing the initial version of this demo and the working network. 47 | 48 | -------------------------------------------------------------------------------- /texture_nets/NoiseFill.lua: -------------------------------------------------------------------------------- 1 | ---------------------------------------------------------- 2 | -- NoiseFill 3 | ---------------------------------------------------------- 4 | -- Fills last `num_noise_channels` channels of an existing `input` tensor with noise. 5 | local NoiseFill, parent = torch.class('nn.NoiseFill', 'nn.Module') 6 | 7 | function NoiseFill:__init(num_noise_channels) 8 | parent.__init(self) 9 | 10 | -- last `num_noise_channels` maps will be filled with noise 11 | self.num_noise_channels = num_noise_channels 12 | self.mult = 1.0 13 | end 14 | 15 | function NoiseFill:updateOutput(input) 16 | self.output = self.output or input:new() 17 | self.output:resizeAs(input) 18 | 19 | 20 | -- copy non-noise part 21 | if self.num_noise_channels ~= input:size(2) then 22 | local ch_to_copy = input:size(2) - self.num_noise_channels 23 | self.output:narrow(2,1,ch_to_copy):copy(input:narrow(2,1,ch_to_copy)) 24 | end 25 | 26 | -- fill noise 27 | if self.num_noise_channels > 0 then 28 | local num_channels = input:size(2) 29 | local first_noise_channel = num_channels - self.num_noise_channels + 1 30 | 31 | self.output:narrow(2,first_noise_channel, self.num_noise_channels):uniform():mul(self.mult) 32 | end 33 | return self.output 34 | end 35 | 36 | function NoiseFill:updateGradInput(input, gradOutput) 37 | self.gradInput:set(gradOutput) 38 | return self.gradInput 39 | end 40 | 41 | -------------------------------------------------------------------------------- /imagenet_classification/demo.lua: -------------------------------------------------------------------------------- 1 | local cv = require 'cv' 2 | require 'cv.highgui' 3 | require 'cv.videoio' 4 | require 'cv.imgproc' 5 | require 'nn' 6 | 7 | local cap = cv.VideoCapture{device=0} 8 | if not cap:isOpened() then 9 | print("Failed to open the default camera") 10 | os.exit(-1) 11 | end 12 | 13 | cv.namedWindow{winname="torch-OpenCV ImageNet classification demo", flags=cv.WINDOW_AUTOSIZE} 14 | local _, frame = cap:read{} 15 | 16 | print '==> Downloading image and network' 17 | local image_url = 'http://upload.wikimedia.org/wikipedia/commons/e/e9/Goldfish3.jpg' 18 | local network_url = 'https://www.dropbox.com/s/npmr5egvjbg7ovb/nin_nobn_final.t7' 19 | local image_name = paths.basename(image_url) 20 | local network_name = paths.basename(network_url) 21 | if not paths.filep(image_name) then os.execute('wget '..image_url) end 22 | if not paths.filep(network_name) then os.execute('wget '..network_url) end 23 | 24 | 25 | print '==> Loading network' 26 | -- Using network in network http://openreview.net/document/9b05a3bb-3a5e-49cb-91f7-0f482af65aea 27 | local net = torch.load(network_name).model:float() 28 | local synset_words = torch.load('synset.t7','ascii') 29 | 30 | local M = 224 31 | 32 | while true do 33 | local w = frame:size(2) 34 | local h = frame:size(1) 35 | 36 | local crop = cv.getRectSubPix{image=frame, patchSize={h,h}, center={w/2, h/2}} 37 | local im = cv.resize{src=crop, dsize={256,256}}:float():div(255) 38 | for i=1,3 do im:select(3,i):add(-net.transform.mean[i]):div(net.transform.std[i]) end 39 | local I = cv.resize{src=im, dsize={M,M}}:permute(3,1,2):clone() 40 | 41 | local _,classes = net:forward(I):view(-1):float():sort(true) 42 | 43 | for i=1,5 do 44 | cv.putText{ 45 | img=crop, 46 | text = synset_words[classes[i]], 47 | org={10,10 + i * 25}, 48 | fontFace=cv.FONT_HERSHEY_DUPLEX, 49 | fontScale=1, 50 | color={255, 255, 0}, 51 | thickness=1 52 | } 53 | end 54 | 55 | cv.imshow{winname="torch-OpenCV ImageNet classification demo", image=crop} 56 | if cv.waitKey{30} >= 0 then break end 57 | 58 | cap:read{image=frame} 59 | end 60 | -------------------------------------------------------------------------------- /texture_nets/stylization.lua: -------------------------------------------------------------------------------- 1 | local cv = require 'cv' 2 | require 'cv.highgui' 3 | require 'cv.videoio' 4 | require 'cv.imgproc' 5 | 6 | require 'nn' 7 | require 'SpatialCircularPadding' 8 | require 'NoiseFill' 9 | local utils = require 'inn.utils' 10 | 11 | require 'image' 12 | require 'nn' 13 | require 'xlua' 14 | 15 | local opt = xlua.envparams{ 16 | frame_height = 512, 17 | video_path = '', 18 | network = './starry.t7', 19 | type = 'float', 20 | } 21 | 22 | 23 | local cap = cv.VideoCapture{opt.video_path ~= '' and opt.video_path or 0} 24 | if not cap:isOpened() then 25 | print("Failed to open the default camera") 26 | os.exit(-1) 27 | end 28 | 29 | cv.namedWindow{opt.network, cv.WINDOW_AUTOSIZE} 30 | local _,frame = cap:read{} 31 | 32 | local function cast(x) 33 | if opt.type == 'float' then 34 | return x:float() 35 | elseif opt.type == 'cuda' then 36 | require 'cunn' 37 | return x:cuda() 38 | elseif opt.type == 'cl' then 39 | require 'clnn' 40 | return x:cl() 41 | end 42 | end 43 | 44 | -- yes, that's true, net takes 0-1 input and output is VGG 45 | local function preprocess(frame) 46 | local frame1 = frame:permute(3,1,2):float() / 255 47 | frame1 = image.scale(frame1, opt.frame_height, opt.frame_height / 2) 48 | return frame1:view(1,table.unpack(frame1:size():totable())) 49 | end 50 | 51 | local function deprocess(img) 52 | local mean_pixel = torch.FloatTensor({103.939, 116.779, 123.68}) 53 | img:add(mean_pixel:view(3, 1, 1):expandAs(img)) 54 | return img 55 | end 56 | 57 | local net = torch.load(opt.network) 58 | cast(net):evaluate() 59 | 60 | -- to enable foldBatchNorm, otherwise it cannot detect conv+BN pairs 61 | local function simplify(net) 62 | for i,v in ipairs(net:findModules'nn.Sequential') do 63 | for j,u in ipairs(v.modules) do 64 | if torch.typename(u) == 'nn.Sequential' and u.modules and #u.modules == 2 then 65 | v:remove(j) 66 | v:insert(u:get(1),j) 67 | v:insert(u:get(2),j+1) 68 | end 69 | end 70 | end 71 | end 72 | 73 | local input = cast(preprocess(frame)) 74 | utils.testSurgery(input, simplify, net) 75 | utils.testSurgery(input, utils.foldBatchNorm, net) 76 | print(net) 77 | 78 | 79 | while true do 80 | local input = preprocess(frame) 81 | local out = deprocess(net(cast(input))[1]:float()) 82 | cv.imshow{opt.network, (torch.clamp(out:permute(2,3,1),0,255)):byte()} 83 | 84 | if cv.waitKey{30} >= 0 then break end 85 | cap:read{frame} 86 | end 87 | -------------------------------------------------------------------------------- /face_recognition/README.md: -------------------------------------------------------------------------------- 1 | Interactive Face Recognition with GPU 2 | === 3 | 4 | To provide an example of how OpenCV's CUDA module can be used in Torch, we have implemented interactive face recognition in this application. 5 | 6 | ## Important warning 7 | 8 | In this very example, the recognition quality may be rather poor as, in fact, the OpenFace's face recognition framework is intended to work in a more complicated way. Here, we didn't locate facial landmarks and estimate head pose, although this is an essential part of the pipeline. Keep this in mind when working with this task, and consult [OpenFace's website](http://cmusatyalab.github.io/openface/) for further information. 9 | 10 | ## How to use it 11 | 12 | Here is how the program is run: 13 | 14 | Usage: `th demo.lua video_source [N [Name1 Name2 ...] ]` 15 | 16 | Where 17 | * *video_source*: 18 | 19 | Video source to capture. 20 | If "camera", then default camera is used. 21 | Otherwise, `video_source` is assumed to be a path to a video file. 22 | 23 | * *N*: 24 | 25 | Number of different people to recognize (2..9). 26 | 27 | * *Name1, Name2, ...*: 28 | 29 | Their names (optional). 30 | 31 | After launched, the program initializes two windows: the "gallery" (for reference face images), and the main window, which shows frames from the selected video source. 32 | 33 | The program starts in the **learning phase**. During it, the user selects a person to be labeled from the gallery by pressing digit keys (1..9), and then double-clicks the red rectangle that contains the corresponding face. The stream can be paused with Space key for convenience. The system is ready to learn when the gallery shows no vertical red line. 34 | 35 | ![screenshot](https://cloud.githubusercontent.com/assets/9570420/13470424/2c5d3106-e0bd-11e5-9319-9f1dbf8c86ab.png) 36 | ![screenshot 1](https://cloud.githubusercontent.com/assets/9570420/13470423/2c5d5064-e0bd-11e5-842c-d99157e22d6c.png) 37 | 38 | Hitting Enter brings the system into the **recognition phase**, where the names are predicted. 39 | 40 | ![screenshot 2](https://cloud.githubusercontent.com/assets/9570420/13530688/b1f694ac-e233-11e5-955c-df71688f472b.png) 41 | ![screenshot 3](https://cloud.githubusercontent.com/assets/9570420/13530687/b1ceebd2-e233-11e5-8947-06684910aeff.png) 42 | 43 | ## How recognition works 44 | 45 | After a face has been detected, its so-called *face descriptor* (a vector of 128 numbers) is extracted by a convolutional neural network from [OpenFace project](http://cmusatyalab.github.io/openface/). After the user has ended filling the gallery, an SVM is trained on these vectors: it tries to separate the descriptors with different labels by parabolic surfaces in 128-dimensional space. Afterwards, during the recognition phase, new descriptors (without labels, obviously) that are extracted from face detection boxes are fed to this SVM to predict their labels. -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | Torch7-OpenCV demos 2 | ================== 3 | 4 | Real-time demos that use deep convolutional neural networks to classify and caption 5 | what they see in real-time from a webcam stream. 6 | 7 | All demos use CPU, but it's trivial to fix them to work with CUDA or OpenCL. 8 | 9 | There's a [Docker image](https://github.com/riomus/torch-opencv-demos-docker) to make installation & experiments easier. 10 | 11 | Otherwise... 12 | 13 | Quick install on OS X: 14 | 15 | ```bash 16 | brew instal opencv3 --with-contrib 17 | OpenCV_DIR=/usr/local/Cellar/opencv3/3.1.0/share/OpenCV luarocks install cv 18 | brew install protobuf 19 | luarocks install loadcaffe 20 | ``` 21 | 22 | In Linux you have to build OpenCV 3 manually. Follow the instructions in 23 | 24 | * https://github.com/VisionLabs/torch-opencv 25 | * https://github.com/szagoruyko/loadcaffe 26 | 27 | # ImageNet classification 28 | 29 | The demo simply takes a central crop from a webcam and uses a small ImageNet 30 | classification pretrained network to classify what it see on it. top-5 predicted 31 | classes are shown on top, the top one is the most probable. 32 | 33 | Run as `th demo.lua` 34 | 35 | Example: 36 | 37 | ![sunglasses](https://cloud.githubusercontent.com/assets/4953728/14815521/2095c832-0bac-11e6-80bc-09b19c13271d.png) 38 | 39 | # Age&Gender prediction 40 | 41 | This demo uses two networks described here http://www.openu.ac.il/home/hassner/projects/cnn_agegender/ 42 | to predict age and gender of the faces that it finds with a simple cascade detector. 43 | 44 | Run as 45 | ``` 46 | th demo.lua video_source [path-to-'haarcascade_frontalface_default.xml'] 47 | ``` 48 | 49 | Where `video_source` is `camera` or path to a video file, and the second argument is optional. 50 | 51 | IMAGINE Lab gives an example: 52 | 53 | ![age&gender](https://cloud.githubusercontent.com/assets/4953728/12299217/fc819f80-ba15-11e5-95de-653c9fda9b83.png) 54 | 55 | NeuralTalk2 demo 56 | ================ 57 | 58 | This demo uses NeuralTalk2 captioning code from Andrej Karpathy: https://github.com/karpathy/neuraltalk2 59 | 60 | The code captions live webcam demo. Follow the installation instructions at 61 | https://github.com/karpathy/neuraltalk2 first and then run the demo as: 62 | 63 | ``` 64 | th videocaptioning.lua -gpuid -1 -model model_id1-501-1448236541_cpu.t7 65 | ``` 66 | 67 | Caption is displayed on top: 68 | 69 | ![neuraltalk2](https://cloud.githubusercontent.com/assets/4953728/14815525/23cfb3aa-0bac-11e6-84fd-dd0f7a33422d.png) 70 | 71 | # Realtime stylization with texture networks 72 | 73 | Check https://github.com/DmitryUlyanov/texture_nets 74 | 75 | ![screen shot 2016-04-25 at 00 08 15](https://cloud.githubusercontent.com/assets/4953728/14781476/fa8a7c1a-0ae2-11e6-88fb-10e2bf418d86.png) 76 | 77 | # Credits 78 | 79 | 2016 Sergey Zagoruyko and Egor Burkov 80 | 81 | Thanks to VisionLabs for putting up https://github.com/VisionLabs/torch-opencv bindings! 82 | -------------------------------------------------------------------------------- /age_gender/demo.lua: -------------------------------------------------------------------------------- 1 | local cv = require 'cv' 2 | require 'cv.objdetect' 3 | require 'cv.highgui' 4 | require 'cv.videoio' 5 | require 'cv.imgproc' 6 | require 'loadcaffe' 7 | 8 | if not arg[1] then 9 | print[[ 10 | Usage: th demo.lua video_source [path-to-'haarcascade_frontalface_default.xml'] 11 | 12 | Where 13 | * video_source: 14 | 15 | Video source to capture. 16 | If "camera", then default camera is used. 17 | Otherwise, `video_source` is assumed to be a path to a video file. 18 | 19 | * path-to-'haarcascade_frontalface_default.xml': 20 | 21 | Optional argument, path to OpenCV's haarcascade_frontalface_default.xml. 22 | Use it if your `locate` command isn't able to find it it automatically. 23 | ]] 24 | os.exit(-1) 25 | end 26 | 27 | -- Viola-Jones face detector 28 | local XMLTarget = 'haarcascades/haarcascade_frontalface_default.xml' 29 | print('Looking for '..XMLTarget..'...') 30 | local command = io.popen('locate '..XMLTarget, 'r') 31 | local locateOutput = command:read() 32 | local _, endIndex = locateOutput:find(XMLTarget) 33 | local detectorParamsFile = locateOutput:sub(1, endIndex) or arg[2] 34 | command:close() 35 | assert(paths.filep(detectorParamsFile), 36 | XMLTarget..' not found! Try using the second cmdline argument') 37 | 38 | local face_cascade = cv.CascadeClassifier{detectorParamsFile} 39 | 40 | local fx = 0.5 -- rescale factor 41 | local M = 227 -- input image size 42 | local ages = {'0-2','4-6','8-13','15-20','25-32','38-43','48-53','60-'} 43 | 44 | local download_list = { 45 | {name='age_net.caffemodel', url='https://github.com/eveningglow/age-and-gender-classification/raw/master/model/age_net.caffemodel'}, 46 | {name='gender_net.caffemodel', url='https://github.com/eveningglow/age-and-gender-classification/raw/master/model/gender_net.caffemodel'}, 47 | {name='deploy_age.prototxt', url='https://github.com/eveningglow/age-and-gender-classification/raw/master/model/deploy_age2.prototxt'}, 48 | {name='deploy_gender.prototxt', url='https://github.com/eveningglow/age-and-gender-classification/raw/master/model/deploy_gender2.prototxt'}, 49 | {name='age_gender_mean.t7', url='https://www.dropbox.com/s/wa61ihl8l9z89e8/age_gender_mean.t7'} 50 | } 51 | 52 | for k,v in ipairs(download_list) do 53 | if not paths.filep(v.name) then os.execute('wget '..v.url..' -O '..v.name) end 54 | end 55 | 56 | local gender_net = loadcaffe.load('./deploy_gender.prototxt', './gender_net.caffemodel'):float() 57 | local age_net = loadcaffe.load('./deploy_age.prototxt', './age_net.caffemodel'):float() 58 | 59 | local img_mean = torch.load'./age_gender_mean.t7':permute(3,1,2):float() 60 | 61 | local cap = cv.VideoCapture{arg[1] == 'camera' and 0 or arg[1]} 62 | assert(cap:isOpened(), 'Failed to open '..arg[1]) 63 | 64 | local ok, frame = cap:read{} 65 | 66 | if not ok then 67 | print("Couldn't retrieve frame!") 68 | os.exit(-1) 69 | end 70 | 71 | while true do 72 | local w = frame:size(2) 73 | local h = frame:size(1) 74 | 75 | local im2 = cv.resize{frame, fx=fx, fy=fx} 76 | cv.cvtColor{im2, dst=im2, code=cv.COLOR_BGR2GRAY} 77 | 78 | local faces = face_cascade:detectMultiScale{im2} 79 | for i=1,faces.size do 80 | local f = faces.data[i] 81 | local x = f.x/fx 82 | local y = f.y/fx 83 | local w = f.width/fx 84 | local h = f.height/fx 85 | 86 | -- crop and prepare image for convnets 87 | local crop = cv.getRectSubPix{ 88 | image=frame, 89 | patchSize={w, h}, 90 | center={x + w/2, y + h/2}, 91 | } 92 | 93 | if crop then 94 | local im = cv.resize{src=crop, dsize={256,256}}:float() 95 | local im2 = im - img_mean 96 | local I = cv.resize{src=im2, dsize={M,M}}:permute(3,1,2):clone() 97 | 98 | -- classify 99 | local gender_out = gender_net:forward(I) 100 | local gender = gender_out[1] > gender_out[2] and 'M' or 'F' 101 | 102 | local age_out = age_net:forward(I) 103 | local _,id = age_out:max(1) 104 | local age = ages[id[1] ] 105 | 106 | cv.rectangle{frame, pt1={x, y+3}, pt2={x + w, y + h}, color={30,255,30}} 107 | cv.putText{ 108 | frame, 109 | gender..': '..age, 110 | org={x, y}, 111 | fontFace=cv.FONT_HERSHEY_DUPLEX, 112 | fontScale=1, 113 | color={255, 255, 0}, 114 | thickness=1 115 | } 116 | end 117 | end 118 | 119 | cv.imshow{"torch-OpenCV Age&Gender demo", frame} 120 | ok = cap:read{frame} 121 | 122 | if cv.waitKey{1} >= 0 or not ok then break end 123 | end 124 | -------------------------------------------------------------------------------- /texture_nets/SpatialCircularPadding.lua: -------------------------------------------------------------------------------- 1 | local SpatialCircularPadding, parent = torch.class('nn.SpatialCircularPadding', 'nn.Module') 2 | 3 | function SpatialCircularPadding:__init(pad_l, pad_r, pad_t, pad_b) 4 | parent.__init(self) 5 | self.pad_l = pad_l 6 | self.pad_r = pad_r or self.pad_l 7 | self.pad_t = pad_t or self.pad_l 8 | self.pad_b = pad_b or self.pad_l 9 | 10 | if self.pad_l < 0 or self.pad_r < 0 or self.pad_t < 0 or self.pad_b < 0 then 11 | error('padding should be > 0') 12 | end 13 | end 14 | 15 | function SpatialCircularPadding:updateOutput(input) 16 | if input:dim() ~= 4 and input:dim() ~= 3 then 17 | error('input must be 3 or 4-dimensional') 18 | end 19 | 20 | local ac = 4 - input:dim() 21 | 22 | -- sizes 23 | local h = input:size(3 - ac) + self.pad_t + self.pad_b 24 | local w = input:size(4- ac) + self.pad_l + self.pad_r 25 | 26 | if w < 1 or h < 1 then error('input is too small') end 27 | 28 | if input:dim() == 4 then 29 | self.output:resize(input:size(1), input:size(2), h, w) 30 | else 31 | self.output:resize(input:size(1), h, w) 32 | end 33 | -- self.output:zero() 34 | 35 | -- crop input if necessary 36 | local c_input = input 37 | 38 | -- crop outout if necessary 39 | local c_output = self.output 40 | c_output = c_output:narrow(3- ac, 1 + self.pad_t, c_output:size(3- ac) - self.pad_t) 41 | c_output = c_output:narrow(3- ac, 1, c_output:size(3- ac) - self.pad_b) 42 | c_output = c_output:narrow(4- ac, 1 + self.pad_l, c_output:size(4- ac) - self.pad_l) 43 | c_output = c_output:narrow(4- ac, 1, c_output:size(4- ac) - self.pad_r) 44 | 45 | -- copy input to output 46 | c_output:copy(c_input) 47 | 48 | ----------------------------------------------------------------------- 49 | -- It should be done like folowing, but it is not clear about corners, 50 | -- Filling them with 0 is bad idea, since NN will find the corners then 51 | -- So use a little weird version 52 | ------------------------------------------------------------------------ 53 | 54 | -- local tb_slice = self.output:narrow(4, self.pad_l+1, input:size(4)) 55 | -- local lr_slice = self.output:narrow(3, self.pad_t+1, input:size(3)) 56 | 57 | -- tb_slice:narrow(3, 1, self.pad_t):copy(input:narrow(3, input:size(3) - self.pad_t + 1, self.pad_t)) 58 | -- tb_slice:narrow(3, input:size(3) + self.pad_t + 1, self.pad_b):copy(input:narrow(3, 1, self.pad_b)) 59 | 60 | -- lr_slice:narrow(4, 1, self.pad_l):copy(input:narrow(4, input:size(4) - self.pad_l + 1, self.pad_l)) 61 | -- lr_slice:narrow(4, input:size(4) + self.pad_l + 1, self.pad_r):copy(input:narrow(4, 1, self.pad_r)) 62 | 63 | -- zero out corners 64 | -- self.output:narrow(4, 1, self.pad_l):narrow(3, 1, self.pad_t):zero() 65 | -- self.output:narrow(4, 1, self.pad_l):narrow(3, input:size(3) + self.pad_t + 1, self.pad_b):zero() 66 | -- self.output:narrow(4, input:size(4) + self.pad_l + 1, self.pad_r):narrow(3, 1, self.pad_t):zero() 67 | -- self.output:narrow(4, input:size(4) + self.pad_l + 1, self.pad_r):narrow(3, input:size(3) + self.pad_t + 1, self.pad_b):zero() 68 | 69 | ----------------------------------------------------------------------- 70 | -- About right, but fills corners with something .. 71 | ----------------------------------------------------------------------- 72 | 73 | self.output:narrow(3- ac,1,self.pad_t):copy(self.output:narrow(3- ac,input:size(3- ac) + 1,self.pad_t)) 74 | self.output:narrow(3- ac,input:size(3- ac) + self.pad_t + 1,self.pad_b):copy(self.output:narrow(3- ac,self.pad_t + 1,self.pad_b)) 75 | 76 | self.output:narrow(4- ac,1,self.pad_l):copy(self.output:narrow(4- ac,input:size(4- ac) + 1,self.pad_l)) 77 | self.output:narrow(4- ac,input:size(4- ac) + self.pad_l + 1,self.pad_r):copy(self.output:narrow(4- ac,self.pad_l+1,self.pad_r)) 78 | 79 | 80 | 81 | return self.output 82 | end 83 | 84 | -- function SpatialCircularPadding:updateGradInput(input, gradOutput) 85 | -- if input:dim() ~= 4 and input:dim() ~= 3 then 86 | -- error('input must be 3 or 4-dimensional') 87 | -- end 88 | 89 | -- -- Do it inplace to save memory 90 | -- self.gradInput = nil 91 | -- local cg_output = gradOutput 92 | 93 | -- cg_output = cg_output:narrow(3, 1 + self.pad_t, cg_output:size(3) - self.pad_t) 94 | -- cg_output = cg_output:narrow(3, 1, cg_output:size(3) - self.pad_b) 95 | -- cg_output = cg_output:narrow(4, 1 + self.pad_l, cg_output:size(4) - self.pad_l) 96 | -- cg_output = cg_output:narrow(4, 1, cg_output:size(4) - self.pad_r) 97 | 98 | 99 | -- -- Border gradient 100 | -- local tb_slice = gradOutput:narrow(4, self.pad_l+1, input:size(4)) 101 | -- local lr_slice = gradOutput:narrow(3, self.pad_t+1, input:size(3)) 102 | 103 | -- cg_output:narrow(3, input:size(3) - self.pad_t + 1, self.pad_t):add(tb_slice:narrow(3, 1, self.pad_t)) 104 | -- cg_output:narrow(3, 1, self.pad_b):add(tb_slice:narrow(3, input:size(3) + self.pad_t + 1, self.pad_b)) 105 | 106 | -- cg_output:narrow(4, input:size(4) - self.pad_l + 1, self.pad_l):add(lr_slice:narrow(4, 1, self.pad_l)) 107 | -- cg_output:narrow(4, 1, self.pad_r):add(lr_slice:narrow(4, input:size(4) + self.pad_l + 1, self.pad_r)) 108 | 109 | 110 | -- self.gradInput = cg_output 111 | 112 | -- return self.gradInput 113 | -- end 114 | 115 | 116 | function SpatialCircularPadding:__tostring__() 117 | return torch.type(self) .. 118 | string.format('(l=%d,r=%d,t=%d,b=%d)', self.pad_l, self.pad_r, 119 | self.pad_t, self.pad_b) 120 | end -------------------------------------------------------------------------------- /face_recognition/demo.lua: -------------------------------------------------------------------------------- 1 | local cv = require 'cv' 2 | require 'cv.highgui' -- GUI: windows, mouse 3 | require 'cv.videoio' -- VideoCapture 4 | require 'cv.imgproc' -- rectangle, putText 5 | require 'cv.cudaobjdetect' -- CascadeClassifier 6 | require 'cv.cudawarping' -- resize 7 | require 'cv.cudaimgproc' -- cvtColor 8 | cv.ml = require 'cv.ml' -- SVM 9 | 10 | require 'cutorch' 11 | require 'cunn' 12 | require 'dpnn' -- nn.Inception 13 | 14 | ------------------------------------------------------------------------------- 15 | -- Describe command line arguments 16 | ------------------------------------------------------------------------------- 17 | if not arg[1] then 18 | print[[ 19 | Usage: th demo.lua video_source [N [Name1 Name2 ...] ] 20 | 21 | Where 22 | * video_source: 23 | 24 | Video source to capture. 25 | If "camera", then default camera is used. 26 | Otherwise, `video_source` is assumed to be a path to a video file. 27 | 28 | * N: 29 | Number of different people to recognize (2..9). 30 | 31 | * Name1, Name2, ...: 32 | 33 | Their names (optional). 34 | ]] 35 | os.exit(-1) 36 | end 37 | 38 | print('') 39 | print('================== Use 1..9 keys to change the person to be labeled ==================') 40 | print('================== Double-click the face to label it ==================') 41 | print('================== Press Space to pause the stream ==================') 42 | print('') 43 | 44 | ------------------------------------------------------------------------------- 45 | -- Set up machine learning models 46 | ------------------------------------------------------------------------------- 47 | -- Viola-Jones face detector 48 | local XMLTarget = 'haarcascades_cuda/haarcascade_frontalface_default.xml' 49 | print('Looking for '..XMLTarget..'...') 50 | local command = io.popen('locate '..XMLTarget, 'r') 51 | local locateOutput = command:read() 52 | local _, endIndex = locateOutput:find(XMLTarget) 53 | local detectorParamsFile = locateOutput:sub(1, endIndex) 54 | command:close() 55 | assert(paths.filep(detectorParamsFile), XMLTarget..' not found!') 56 | 57 | local faceDetector = cv.cuda.CascadeClassifier{detectorParamsFile} 58 | 59 | -- OpenFace convolutional neural network face descriptor 60 | print('Loading the network...') 61 | local networkURL = 'http://openface-models.storage.cmusatyalab.org/nn4.small2.v1.t7' 62 | local networkName = paths.basename(networkURL) 63 | if not paths.filep(networkName) then os.execute('wget '..networkURL) end 64 | 65 | local network = torch.load(networkName) 66 | network:cuda() -- move network to GPU 67 | local netInputSize = 96 68 | local netOutputSize = 128 69 | network:evaluate() 70 | local netInput = torch.CudaTensor(3, netInputSize, netInputSize) 71 | local netInputHWC = torch.CudaTensor(netInputSize, netInputSize, 3) 72 | 73 | -- SVM to classify descriptors in recognition phase 74 | local svm = cv.ml.SVM{} 75 | svm:setType {cv.ml.SVM_C_SVC} 76 | svm:setKernel {cv.ml.SVM_POLY} 77 | svm:setDegree {2} 78 | svm:setTermCriteria {{cv.TermCriteria_MAX_ITER, 100, 1e-6}} 79 | 80 | ------------------------------------------------------------------------------- 81 | -- Set up video stream and GUI, unpack input arguments 82 | ------------------------------------------------------------------------------- 83 | local capture = cv.VideoCapture{arg[1] == 'camera' and 0 or arg[1]} 84 | assert(capture:isOpened(), 'Failed to open '..arg[1]) 85 | 86 | -- create two windows 87 | cv.namedWindow{'Stream window'} 88 | cv.namedWindow{ 'Faces window'} 89 | cv.setWindowTitle{'Faces window', 'Grabbed faces'} 90 | cv.moveWindow{'Stream window', 5, 5} 91 | cv.moveWindow{'Faces window', 700, 100} 92 | 93 | local N = assert(tonumber(arg[2] or '2')) 94 | assert(N < 10 and N > 0 and N == math.floor(N)) 95 | 96 | -- prepare the "face gallery" 97 | local thumbnailSize = 64 98 | local maxThumbnails = 10 99 | -- white background 100 | local gallery = torch.ByteTensor(thumbnailSize*N, thumbnailSize*maxThumbnails + 100, 3):fill(255) 101 | -- black stripes 102 | for i = 1,N-1 do 103 | gallery:select(1, thumbnailSize*i):zero() 104 | end 105 | gallery:select(2, 100):zero() 106 | gallery:select(2, 100 + 2*thumbnailSize):select(2, 1):fill(30) 107 | gallery:select(2, 100 + 2*thumbnailSize):select(2, 2):fill(30) 108 | 109 | local peopleNames = {} 110 | for i = 1,N do 111 | peopleNames[i] = arg[2 + i] or 'Person #'..i 112 | cv.putText{ 113 | gallery, peopleNames[i]:sub(1,10), {2, thumbnailSize*(i-1) + 36}, 114 | fontFace=cv.FONT_HERSHEY_SIMPLEX, fontScale=0.5, color={160,30,30}} 115 | end 116 | 117 | local stillLabeling = true 118 | local pause = false 119 | local currentPerson 120 | 121 | local function updateFaceNumber(faceNumber) 122 | if faceNumber > N then return end 123 | currentPerson = faceNumber 124 | cv.setWindowTitle{ 125 | 'Stream window', 126 | 'Labeling '..peopleNames[faceNumber]..'\'s face. Press Enter when done'} 127 | end 128 | 129 | updateFaceNumber(1) 130 | 131 | local people = {} 132 | for i = 1,N do people[i] = {} end 133 | 134 | local function enoughFaces() 135 | local minNumber = 1e9 136 | for i = 1,N do minNumber = math.min(minNumber, #people[i]) end 137 | return minNumber >= 2 138 | end 139 | 140 | -- ByteTensor that comes from the camera 141 | local _, frame = capture:read{} 142 | -- CudaTensor that houses `frame` 143 | local frameCUDA = torch.CudaTensor(frame:size()) 144 | 145 | local scaleFactor = 0.5 146 | -- CudaTensor where the downsampled and desaturated `frameCUDA` resides 147 | local frameCUDAGray = torch.CudaTensor((#frame)[1] * scaleFactor, (#frame)[2] * scaleFactor) 148 | 149 | -- accomodation for cropped faces on GPU 150 | local bigFaceCUDA = frameCUDA:clone() 151 | 152 | -- RectArray describing the faces found 153 | local faceRects 154 | 155 | ------------------------------------------------------------------------------- 156 | -- Given a ByteTensor and bounding box, compute face descriptor with CNN on GPU 157 | ------------------------------------------------------------------------------- 158 | local function getDescriptor(croppedFace, rect) 159 | -- copy face to GPU 160 | local smallFaceCUDA = bigFaceCUDA:narrow(1, 1, rect.height-2):narrow(2, 1, rect.width-2) 161 | smallFaceCUDA:copy(croppedFace) 162 | 163 | -- rescale it to network input size 164 | cv.cuda.resize{smallFaceCUDA, {netInputSize, netInputSize}, dst=netInputHWC} 165 | netInput:copy(netInputHWC:permute(3,1,2)) 166 | 167 | -- pass it forward through CNN 168 | for i = 1,3 do 169 | netInput[i]:div(255) 170 | end 171 | return network:forward(netInput:view(1, 3, netInputSize, netInputSize)):float() 172 | end 173 | 174 | ------------------------------------------------------------------------------- 175 | -- The function executed at mouse double-click 176 | ------------------------------------------------------------------------------- 177 | local function onMouse(event, x, y, flags) 178 | if not faceRects or event ~= cv.EVENT_LBUTTONDBLCLK or not stillLabeling then 179 | return 180 | end 181 | 182 | -- find a matching rectangle from faceRects 183 | for i = 1,faceRects.size do 184 | local f = faceRects.data[i] 185 | 186 | -- check if click location is inside bounding box 187 | if y >= f.y and y <= f.y + f.height and x >= f.x and x <= f.x + f.width then 188 | -- crop the face 189 | local croppedFace = 190 | cv.getRectSubPix{ 191 | frame, 192 | {f.width-2, f.height-2}, 193 | {f.x + f.width/2, f.y + f.height/2}} 194 | 195 | if #people[currentPerson] < maxThumbnails then 196 | -- get slice for copying 197 | local faceInGallery = gallery 198 | :narrow(1, 1 + thumbnailSize*(currentPerson-1), thumbnailSize) 199 | :narrow(2, 101 + thumbnailSize * #people[currentPerson], thumbnailSize) 200 | -- show image in gallery 201 | cv.resize{croppedFace, {thumbnailSize, thumbnailSize}, dst=faceInGallery} 202 | end 203 | 204 | local descriptor = getDescriptor(croppedFace, f) 205 | 206 | -- save descriptor for future SVM training 207 | table.insert(people[currentPerson], descriptor) 208 | break 209 | end 210 | end 211 | end 212 | 213 | cv.setMouseCallback{'Stream window', onMouse} 214 | 215 | local KEY_1 = 49 216 | local KEY_9 = 57 217 | local KEY_Space = 32 218 | local KEY_Enter = 10 219 | local KEY_Esc = 27 220 | 221 | ------------------------------------------------------------------------------- 222 | -- The main loop 223 | ------------------------------------------------------------------------------- 224 | while true do 225 | if not pause then 226 | -- upload image to GPU and normalize it from [0..255] to [0..1] 227 | frameCUDA:copy(frame):div(255) 228 | -- convert to grayscale and store result in original image's blue (first) channel 229 | cv.cuda.cvtColor{frameCUDA, frameCUDA:select(3,1), cv.COLOR_BGR2GRAY} 230 | -- resize it 231 | cv.cuda.resize{frameCUDA:select(3,1), dst=frameCUDAGray, fx=scaleFactor, fy=scaleFactor} 232 | 233 | -- detect faces in downsampled image 234 | faceRects = faceDetector:detectMultiScale{frameCUDAGray} 235 | -- convert faces to RectArray from OpenCV-CUDA's internal representation 236 | faceRects = faceDetector:convert{faceRects} 237 | 238 | -- draw faces 239 | for i = 1,faceRects.size do 240 | local f = faceRects.data[i] 241 | -- translate face coordinates to the original big image 242 | f.x = f.x / scaleFactor 243 | f.y = f.y / scaleFactor 244 | f.width = f.width / scaleFactor 245 | f.height = f.height / scaleFactor 246 | 247 | cv.rectangle{ 248 | frame, {f.x, f.y}, {f.x + f.width, f.y + f.height}, 249 | color = {30,30,180}, thickness = 2} 250 | end 251 | end 252 | 253 | local key = cv.waitKey{20} % 256 254 | 255 | if stillLabeling then 256 | ----------------------------------------------------------------------- 257 | -- Labeling phase 258 | ----------------------------------------------------------------------- 259 | if key >= KEY_1 and key <= KEY_9 then 260 | -- key is a digit: change current number of face to be labeled 261 | updateFaceNumber(key-KEY_1+1) 262 | elseif key == KEY_Space then 263 | -- key is Space : set pause 264 | pause = not pause 265 | elseif key == KEY_Enter then 266 | -- key is Enter : end labeling if there are at least 2 samples for each face 267 | if enoughFaces() then 268 | stillLabeling = false 269 | cv.setWindowTitle{'Stream window', 'Live Recognition'} 270 | 271 | -- prepare data for feeding to SVM 272 | local totalFaces = 0 273 | for i = 1,N do 274 | totalFaces = totalFaces + #people[i] 275 | end 276 | 277 | local svmDataX = torch.FloatTensor(totalFaces, netOutputSize) 278 | local svmDataY = {} 279 | 280 | -- the data is traditionally presented row-wise 281 | for class = 1,N do 282 | for i = 1,#people[class] do 283 | table.insert(svmDataY, class) 284 | svmDataX[#svmDataY]:copy(people[class][i]) 285 | end 286 | end 287 | svmDataY = torch.IntTensor(svmDataY) 288 | 289 | svm:train{svmDataX, cv.ml.ROW_SAMPLE, svmDataY} 290 | end 291 | elseif key == KEY_Esc then 292 | -- key is Esc : quit 293 | os.exit(0) 294 | end 295 | else 296 | ----------------------------------------------------------------------- 297 | -- Recognition phase 298 | ----------------------------------------------------------------------- 299 | if key == KEY_Space then 300 | -- key is Space : set pause 301 | pause = not pause 302 | elseif key == KEY_Esc then 303 | -- key is Esc : quit 304 | os.exit(0) 305 | end 306 | 307 | for i = 1,faceRects.size do 308 | local f = faceRects.data[i] 309 | 310 | -- crop the face 311 | local croppedFace = 312 | cv.getRectSubPix{ 313 | frame, 314 | {f.width-2, f.height-2}, 315 | {f.x + f.width/2, f.y + f.height/2}} 316 | 317 | -- get descriptor 318 | local descriptor = getDescriptor(croppedFace, f) 319 | -- feed it to SVM, get class prediction 320 | local person = svm:predict{descriptor:view(1, netOutputSize)} 321 | -- draw predicted name above the rectangle 322 | cv.putText{ 323 | frame, peopleNames[person], {f.x, f.y-3}, 324 | fontFace=cv.FONT_HERSHEY_SIMPLEX, color={255,255,30}, 325 | fontScale=1, thickness=2} 326 | end 327 | end 328 | 329 | cv.imshow{'Stream window', frame} 330 | cv.imshow{'Faces window', gallery} 331 | 332 | if not pause then capture:read{frame} end 333 | end 334 | -------------------------------------------------------------------------------- /imagenet_classification/synset.t7: -------------------------------------------------------------------------------- 1 | 3 2 | 1 3 | 1000 4 | 1 5 | 1 6 | 2 7 | 18 8 | tench, Tinca tinca 9 | 1 10 | 2 11 | 2 12 | 27 13 | goldfish, Carassius auratus 14 | 1 15 | 3 16 | 2 17 | 83 18 | great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias 19 | 1 20 | 4 21 | 2 22 | 31 23 | tiger shark, Galeocerdo cuvieri 24 | 1 25 | 5 26 | 2 27 | 28 28 | hammerhead, hammerhead shark 29 | 1 30 | 6 31 | 2 32 | 42 33 | electric ray, crampfish, numbfish, torpedo 34 | 1 35 | 7 36 | 2 37 | 8 38 | stingray 39 | 1 40 | 8 41 | 2 42 | 4 43 | cock 44 | 1 45 | 9 46 | 2 47 | 3 48 | hen 49 | 1 50 | 10 51 | 2 52 | 25 53 | ostrich, Struthio camelus 54 | 1 55 | 11 56 | 2 57 | 35 58 | brambling, Fringilla montifringilla 59 | 1 60 | 12 61 | 2 62 | 30 63 | goldfinch, Carduelis carduelis 64 | 1 65 | 13 66 | 2 67 | 41 68 | house finch, linnet, Carpodacus mexicanus 69 | 1 70 | 14 71 | 2 72 | 15 73 | junco, snowbird 74 | 1 75 | 15 76 | 2 77 | 59 78 | indigo bunting, indigo finch, indigo bird, Passerina cyanea 79 | 1 80 | 16 81 | 2 82 | 41 83 | robin, American robin, Turdus migratorius 84 | 1 85 | 17 86 | 2 87 | 6 88 | bulbul 89 | 1 90 | 18 91 | 2 92 | 3 93 | jay 94 | 1 95 | 19 96 | 2 97 | 6 98 | magpie 99 | 1 100 | 20 101 | 2 102 | 9 103 | chickadee 104 | 1 105 | 21 106 | 2 107 | 19 108 | water ouzel, dipper 109 | 1 110 | 22 111 | 2 112 | 4 113 | kite 114 | 1 115 | 23 116 | 2 117 | 52 118 | bald eagle, American eagle, Haliaeetus leucocephalus 119 | 1 120 | 24 121 | 2 122 | 7 123 | vulture 124 | 1 125 | 25 126 | 2 127 | 46 128 | great grey owl, great gray owl, Strix nebulosa 129 | 1 130 | 26 131 | 2 132 | 47 133 | European fire salamander, Salamandra salamandra 134 | 1 135 | 27 136 | 2 137 | 30 138 | common newt, Triturus vulgaris 139 | 1 140 | 28 141 | 2 142 | 3 143 | eft 144 | 1 145 | 29 146 | 2 147 | 39 148 | spotted salamander, Ambystoma maculatum 149 | 1 150 | 30 151 | 2 152 | 39 153 | axolotl, mud puppy, Ambystoma mexicanum 154 | 1 155 | 31 156 | 2 157 | 26 158 | bullfrog, Rana catesbeiana 159 | 1 160 | 32 161 | 2 162 | 20 163 | tree frog, tree-frog 164 | 1 165 | 33 166 | 2 167 | 63 168 | tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui 169 | 1 170 | 34 171 | 2 172 | 46 173 | loggerhead, loggerhead turtle, Caretta caretta 174 | 1 175 | 35 176 | 2 177 | 70 178 | leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea 179 | 1 180 | 36 181 | 2 182 | 10 183 | mud turtle 184 | 1 185 | 37 186 | 2 187 | 8 188 | terrapin 189 | 1 190 | 38 191 | 2 192 | 24 193 | box turtle, box tortoise 194 | 1 195 | 39 196 | 2 197 | 12 198 | banded gecko 199 | 1 200 | 40 201 | 2 202 | 36 203 | common iguana, iguana, Iguana iguana 204 | 1 205 | 41 206 | 2 207 | 46 208 | American chameleon, anole, Anolis carolinensis 209 | 1 210 | 42 211 | 2 212 | 25 213 | whiptail, whiptail lizard 214 | 1 215 | 43 216 | 2 217 | 5 218 | agama 219 | 1 220 | 44 221 | 2 222 | 36 223 | frilled lizard, Chlamydosaurus kingi 224 | 1 225 | 45 226 | 2 227 | 16 228 | alligator lizard 229 | 1 230 | 46 231 | 2 232 | 33 233 | Gila monster, Heloderma suspectum 234 | 1 235 | 47 236 | 2 237 | 29 238 | green lizard, Lacerta viridis 239 | 1 240 | 48 241 | 2 242 | 39 243 | African chameleon, Chamaeleo chamaeleon 244 | 1 245 | 49 246 | 2 247 | 78 248 | Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis 249 | 1 250 | 50 251 | 2 252 | 55 253 | African crocodile, Nile crocodile, Crocodylus niloticus 254 | 1 255 | 51 256 | 2 257 | 45 258 | American alligator, Alligator mississipiensis 259 | 1 260 | 52 261 | 2 262 | 11 263 | triceratops 264 | 1 265 | 53 266 | 2 267 | 45 268 | thunder snake, worm snake, Carphophis amoenus 269 | 1 270 | 54 271 | 2 272 | 45 273 | ringneck snake, ring-necked snake, ring snake 274 | 1 275 | 55 276 | 2 277 | 37 278 | hognose snake, puff adder, sand viper 279 | 1 280 | 56 281 | 2 282 | 24 283 | green snake, grass snake 284 | 1 285 | 57 286 | 2 287 | 21 288 | king snake, kingsnake 289 | 1 290 | 58 291 | 2 292 | 25 293 | garter snake, grass snake 294 | 1 295 | 59 296 | 2 297 | 11 298 | water snake 299 | 1 300 | 60 301 | 2 302 | 10 303 | vine snake 304 | 1 305 | 61 306 | 2 307 | 32 308 | night snake, Hypsiglena torquata 309 | 1 310 | 62 311 | 2 312 | 40 313 | boa constrictor, Constrictor constrictor 314 | 1 315 | 63 316 | 2 317 | 37 318 | rock python, rock snake, Python sebae 319 | 1 320 | 64 321 | 2 322 | 23 323 | Indian cobra, Naja naja 324 | 1 325 | 65 326 | 2 327 | 11 328 | green mamba 329 | 1 330 | 66 331 | 2 332 | 9 333 | sea snake 334 | 1 335 | 67 336 | 2 337 | 65 338 | horned viper, cerastes, sand viper, horned asp, Cerastes cornutus 339 | 1 340 | 68 341 | 2 342 | 57 343 | diamondback, diamondback rattlesnake, Crotalus adamanteus 344 | 1 345 | 69 346 | 2 347 | 49 348 | sidewinder, horned rattlesnake, Crotalus cerastes 349 | 1 350 | 70 351 | 2 352 | 9 353 | trilobite 354 | 1 355 | 71 356 | 2 357 | 45 358 | harvestman, daddy longlegs, Phalangium opilio 359 | 1 360 | 72 361 | 2 362 | 8 363 | scorpion 364 | 1 365 | 73 366 | 2 367 | 46 368 | black and gold garden spider, Argiope aurantia 369 | 1 370 | 74 371 | 2 372 | 30 373 | barn spider, Araneus cavaticus 374 | 1 375 | 75 376 | 2 377 | 31 378 | garden spider, Aranea diademata 379 | 1 380 | 76 381 | 2 382 | 32 383 | black widow, Latrodectus mactans 384 | 1 385 | 77 386 | 2 387 | 9 388 | tarantula 389 | 1 390 | 78 391 | 2 392 | 27 393 | wolf spider, hunting spider 394 | 1 395 | 79 396 | 2 397 | 4 398 | tick 399 | 1 400 | 80 401 | 2 402 | 9 403 | centipede 404 | 1 405 | 81 406 | 2 407 | 12 408 | black grouse 409 | 1 410 | 82 411 | 2 412 | 9 413 | ptarmigan 414 | 1 415 | 83 416 | 2 417 | 41 418 | ruffed grouse, partridge, Bonasa umbellus 419 | 1 420 | 84 421 | 2 422 | 45 423 | prairie chicken, prairie grouse, prairie fowl 424 | 1 425 | 85 426 | 2 427 | 7 428 | peacock 429 | 1 430 | 86 431 | 2 432 | 5 433 | quail 434 | 1 435 | 87 436 | 2 437 | 9 438 | partridge 439 | 1 440 | 88 441 | 2 442 | 47 443 | African grey, African gray, Psittacus erithacus 444 | 1 445 | 89 446 | 2 447 | 5 448 | macaw 449 | 1 450 | 90 451 | 2 452 | 60 453 | sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita 454 | 1 455 | 91 456 | 2 457 | 8 458 | lorikeet 459 | 1 460 | 92 461 | 2 462 | 6 463 | coucal 464 | 1 465 | 93 466 | 2 467 | 9 468 | bee eater 469 | 1 470 | 94 471 | 2 472 | 8 473 | hornbill 474 | 1 475 | 95 476 | 2 477 | 11 478 | hummingbird 479 | 1 480 | 96 481 | 2 482 | 7 483 | jacamar 484 | 1 485 | 97 486 | 2 487 | 6 488 | toucan 489 | 1 490 | 98 491 | 2 492 | 5 493 | drake 494 | 1 495 | 99 496 | 2 497 | 39 498 | red-breasted merganser, Mergus serrator 499 | 1 500 | 100 501 | 2 502 | 5 503 | goose 504 | 1 505 | 101 506 | 2 507 | 26 508 | black swan, Cygnus atratus 509 | 1 510 | 102 511 | 2 512 | 6 513 | tusker 514 | 1 515 | 103 516 | 2 517 | 33 518 | echidna, spiny anteater, anteater 519 | 1 520 | 104 521 | 2 522 | 87 523 | platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus 524 | 1 525 | 105 526 | 2 527 | 23 528 | wallaby, brush kangaroo 529 | 1 530 | 106 531 | 2 532 | 69 533 | koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus 534 | 1 535 | 107 536 | 2 537 | 6 538 | wombat 539 | 1 540 | 108 541 | 2 542 | 9 543 | jellyfish 544 | 1 545 | 109 546 | 2 547 | 20 548 | sea anemone, anemone 549 | 1 550 | 110 551 | 2 552 | 11 553 | brain coral 554 | 1 555 | 111 556 | 2 557 | 23 558 | flatworm, platyhelminth 559 | 1 560 | 112 561 | 2 562 | 34 563 | nematode, nematode worm, roundworm 564 | 1 565 | 113 566 | 2 567 | 5 568 | conch 569 | 1 570 | 114 571 | 2 572 | 5 573 | snail 574 | 1 575 | 115 576 | 2 577 | 4 578 | slug 579 | 1 580 | 116 581 | 2 582 | 20 583 | sea slug, nudibranch 584 | 1 585 | 117 586 | 2 587 | 54 588 | chiton, coat-of-mail shell, sea cradle, polyplacophore 589 | 1 590 | 118 591 | 2 592 | 45 593 | chambered nautilus, pearly nautilus, nautilus 594 | 1 595 | 119 596 | 2 597 | 31 598 | Dungeness crab, Cancer magister 599 | 1 600 | 120 601 | 2 602 | 27 603 | rock crab, Cancer irroratus 604 | 1 605 | 121 606 | 2 607 | 12 608 | fiddler crab 609 | 1 610 | 122 611 | 2 612 | 86 613 | king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica 614 | 1 615 | 123 616 | 2 617 | 69 618 | American lobster, Northern lobster, Maine lobster, Homarus americanus 619 | 1 620 | 124 621 | 2 622 | 72 623 | spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish 624 | 1 625 | 125 626 | 2 627 | 38 628 | crayfish, crawfish, crawdad, crawdaddy 629 | 1 630 | 126 631 | 2 632 | 11 633 | hermit crab 634 | 1 635 | 127 636 | 2 637 | 6 638 | isopod 639 | 1 640 | 128 641 | 2 642 | 28 643 | white stork, Ciconia ciconia 644 | 1 645 | 129 646 | 2 647 | 26 648 | black stork, Ciconia nigra 649 | 1 650 | 130 651 | 2 652 | 9 653 | spoonbill 654 | 1 655 | 131 656 | 2 657 | 8 658 | flamingo 659 | 1 660 | 132 661 | 2 662 | 35 663 | little blue heron, Egretta caerulea 664 | 1 665 | 133 666 | 2 667 | 48 668 | American egret, great white heron, Egretta albus 669 | 1 670 | 134 671 | 2 672 | 7 673 | bittern 674 | 1 675 | 135 676 | 2 677 | 5 678 | crane 679 | 1 680 | 136 681 | 2 682 | 22 683 | limpkin, Aramus pictus 684 | 1 685 | 137 686 | 2 687 | 39 688 | European gallinule, Porphyrio porphyrio 689 | 1 690 | 138 691 | 2 692 | 62 693 | American coot, marsh hen, mud hen, water hen, Fulica americana 694 | 1 695 | 139 696 | 2 697 | 7 698 | bustard 699 | 1 700 | 140 701 | 2 702 | 35 703 | ruddy turnstone, Arenaria interpres 704 | 1 705 | 141 706 | 2 707 | 43 708 | red-backed sandpiper, dunlin, Erolia alpina 709 | 1 710 | 142 711 | 2 712 | 24 713 | redshank, Tringa totanus 714 | 1 715 | 143 716 | 2 717 | 9 718 | dowitcher 719 | 1 720 | 144 721 | 2 722 | 29 723 | oystercatcher, oyster catcher 724 | 1 725 | 145 726 | 2 727 | 7 728 | pelican 729 | 1 730 | 146 731 | 2 732 | 36 733 | king penguin, Aptenodytes patagonica 734 | 1 735 | 147 736 | 2 737 | 20 738 | albatross, mollymawk 739 | 1 740 | 148 741 | 2 742 | 79 743 | grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus 744 | 1 745 | 149 746 | 2 747 | 59 748 | killer whale, killer, orca, grampus, sea wolf, Orcinus orca 749 | 1 750 | 150 751 | 2 752 | 20 753 | dugong, Dugong dugon 754 | 1 755 | 151 756 | 2 757 | 8 758 | sea lion 759 | 1 760 | 152 761 | 2 762 | 9 763 | Chihuahua 764 | 1 765 | 153 766 | 2 767 | 16 768 | Japanese spaniel 769 | 1 770 | 154 771 | 2 772 | 37 773 | Maltese dog, Maltese terrier, Maltese 774 | 1 775 | 155 776 | 2 777 | 25 778 | Pekinese, Pekingese, Peke 779 | 1 780 | 156 781 | 2 782 | 8 783 | Shih-Tzu 784 | 1 785 | 157 786 | 2 787 | 16 788 | Blenheim spaniel 789 | 1 790 | 158 791 | 2 792 | 8 793 | papillon 794 | 1 795 | 159 796 | 2 797 | 11 798 | toy terrier 799 | 1 800 | 160 801 | 2 802 | 19 803 | Rhodesian ridgeback 804 | 1 805 | 161 806 | 2 807 | 20 808 | Afghan hound, Afghan 809 | 1 810 | 162 811 | 2 812 | 20 813 | basset, basset hound 814 | 1 815 | 163 816 | 2 817 | 6 818 | beagle 819 | 1 820 | 164 821 | 2 822 | 23 823 | bloodhound, sleuthhound 824 | 1 825 | 165 826 | 2 827 | 8 828 | bluetick 829 | 1 830 | 166 831 | 2 832 | 23 833 | black-and-tan coonhound 834 | 1 835 | 167 836 | 2 837 | 29 838 | Walker hound, Walker foxhound 839 | 1 840 | 168 841 | 2 842 | 16 843 | English foxhound 844 | 1 845 | 169 846 | 2 847 | 7 848 | redbone 849 | 1 850 | 170 851 | 2 852 | 25 853 | borzoi, Russian wolfhound 854 | 1 855 | 171 856 | 2 857 | 15 858 | Irish wolfhound 859 | 1 860 | 172 861 | 2 862 | 17 863 | Italian greyhound 864 | 1 865 | 173 866 | 2 867 | 7 868 | whippet 869 | 1 870 | 174 871 | 2 872 | 28 873 | Ibizan hound, Ibizan Podenco 874 | 1 875 | 175 876 | 2 877 | 28 878 | Norwegian elkhound, elkhound 879 | 1 880 | 176 881 | 2 882 | 23 883 | otterhound, otter hound 884 | 1 885 | 177 886 | 2 887 | 21 888 | Saluki, gazelle hound 889 | 1 890 | 178 891 | 2 892 | 29 893 | Scottish deerhound, deerhound 894 | 1 895 | 179 896 | 2 897 | 10 898 | Weimaraner 899 | 1 900 | 180 901 | 2 902 | 53 903 | Staffordshire bullterrier, Staffordshire bull terrier 904 | 1 905 | 181 906 | 2 907 | 98 908 | American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier 909 | 1 910 | 182 911 | 2 912 | 18 913 | Bedlington terrier 914 | 1 915 | 183 916 | 2 917 | 14 918 | Border terrier 919 | 1 920 | 184 921 | 2 922 | 18 923 | Kerry blue terrier 924 | 1 925 | 185 926 | 2 927 | 13 928 | Irish terrier 929 | 1 930 | 186 931 | 2 932 | 15 933 | Norfolk terrier 934 | 1 935 | 187 936 | 2 937 | 15 938 | Norwich terrier 939 | 1 940 | 188 941 | 2 942 | 17 943 | Yorkshire terrier 944 | 1 945 | 189 946 | 2 947 | 23 948 | wire-haired fox terrier 949 | 1 950 | 190 951 | 2 952 | 16 953 | Lakeland terrier 954 | 1 955 | 191 956 | 2 957 | 26 958 | Sealyham terrier, Sealyham 959 | 1 960 | 192 961 | 2 962 | 26 963 | Airedale, Airedale terrier 964 | 1 965 | 193 966 | 2 967 | 20 968 | cairn, cairn terrier 969 | 1 970 | 194 971 | 2 972 | 18 973 | Australian terrier 974 | 1 975 | 195 976 | 2 977 | 38 978 | Dandie Dinmont, Dandie Dinmont terrier 979 | 1 980 | 196 981 | 2 982 | 27 983 | Boston bull, Boston terrier 984 | 1 985 | 197 986 | 2 987 | 19 988 | miniature schnauzer 989 | 1 990 | 198 991 | 2 992 | 15 993 | giant schnauzer 994 | 1 995 | 199 996 | 2 997 | 18 998 | standard schnauzer 999 | 1 1000 | 200 1001 | 2 1002 | 41 1003 | Scotch terrier, Scottish terrier, Scottie 1004 | 1 1005 | 201 1006 | 2 1007 | 34 1008 | Tibetan terrier, chrysanthemum dog 1009 | 1 1010 | 202 1011 | 2 1012 | 27 1013 | silky terrier, Sydney silky 1014 | 1 1015 | 203 1016 | 2 1017 | 27 1018 | soft-coated wheaten terrier 1019 | 1 1020 | 204 1021 | 2 1022 | 27 1023 | West Highland white terrier 1024 | 1 1025 | 205 1026 | 2 1027 | 17 1028 | Lhasa, Lhasa apso 1029 | 1 1030 | 206 1031 | 2 1032 | 21 1033 | flat-coated retriever 1034 | 1 1035 | 207 1036 | 2 1037 | 22 1038 | curly-coated retriever 1039 | 1 1040 | 208 1041 | 2 1042 | 16 1043 | golden retriever 1044 | 1 1045 | 209 1046 | 2 1047 | 18 1048 | Labrador retriever 1049 | 1 1050 | 210 1051 | 2 1052 | 24 1053 | Chesapeake Bay retriever 1054 | 1 1055 | 211 1056 | 2 1057 | 27 1058 | German short-haired pointer 1059 | 1 1060 | 212 1061 | 2 1062 | 25 1063 | vizsla, Hungarian pointer 1064 | 1 1065 | 213 1066 | 2 1067 | 14 1068 | English setter 1069 | 1 1070 | 214 1071 | 2 1072 | 24 1073 | Irish setter, red setter 1074 | 1 1075 | 215 1076 | 2 1077 | 13 1078 | Gordon setter 1079 | 1 1080 | 216 1081 | 2 1082 | 16 1083 | Brittany spaniel 1084 | 1 1085 | 217 1086 | 2 1087 | 24 1088 | clumber, clumber spaniel 1089 | 1 1090 | 218 1091 | 2 1092 | 42 1093 | English springer, English springer spaniel 1094 | 1 1095 | 219 1096 | 2 1097 | 22 1098 | Welsh springer spaniel 1099 | 1 1100 | 220 1101 | 2 1102 | 46 1103 | cocker spaniel, English cocker spaniel, cocker 1104 | 1 1105 | 221 1106 | 2 1107 | 14 1108 | Sussex spaniel 1109 | 1 1110 | 222 1111 | 2 1112 | 19 1113 | Irish water spaniel 1114 | 1 1115 | 223 1116 | 2 1117 | 6 1118 | kuvasz 1119 | 1 1120 | 224 1121 | 2 1122 | 10 1123 | schipperke 1124 | 1 1125 | 225 1126 | 2 1127 | 11 1128 | groenendael 1129 | 1 1130 | 226 1131 | 2 1132 | 8 1133 | malinois 1134 | 1 1135 | 227 1136 | 2 1137 | 6 1138 | briard 1139 | 1 1140 | 228 1141 | 2 1142 | 6 1143 | kelpie 1144 | 1 1145 | 229 1146 | 2 1147 | 8 1148 | komondor 1149 | 1 1150 | 230 1151 | 2 1152 | 29 1153 | Old English sheepdog, bobtail 1154 | 1 1155 | 231 1156 | 2 1157 | 47 1158 | Shetland sheepdog, Shetland sheep dog, Shetland 1159 | 1 1160 | 232 1161 | 2 1162 | 6 1163 | collie 1164 | 1 1165 | 233 1166 | 2 1167 | 13 1168 | Border collie 1169 | 1 1170 | 234 1171 | 2 1172 | 43 1173 | Bouvier des Flandres, Bouviers des Flandres 1174 | 1 1175 | 235 1176 | 2 1177 | 10 1178 | Rottweiler 1179 | 1 1180 | 236 1181 | 2 1182 | 65 1183 | German shepherd, German shepherd dog, German police dog, alsatian 1184 | 1 1185 | 237 1186 | 2 1187 | 27 1188 | Doberman, Doberman pinscher 1189 | 1 1190 | 238 1191 | 2 1192 | 18 1193 | miniature pinscher 1194 | 1 1195 | 239 1196 | 2 1197 | 26 1198 | Greater Swiss Mountain dog 1199 | 1 1200 | 240 1201 | 2 1202 | 20 1203 | Bernese mountain dog 1204 | 1 1205 | 241 1206 | 2 1207 | 11 1208 | Appenzeller 1209 | 1 1210 | 242 1211 | 2 1212 | 11 1213 | EntleBucher 1214 | 1 1215 | 243 1216 | 2 1217 | 5 1218 | boxer 1219 | 1 1220 | 244 1221 | 2 1222 | 12 1223 | bull mastiff 1224 | 1 1225 | 245 1226 | 2 1227 | 15 1228 | Tibetan mastiff 1229 | 1 1230 | 246 1231 | 2 1232 | 14 1233 | French bulldog 1234 | 1 1235 | 247 1236 | 2 1237 | 10 1238 | Great Dane 1239 | 1 1240 | 248 1241 | 2 1242 | 25 1243 | Saint Bernard, St Bernard 1244 | 1 1245 | 249 1246 | 2 1247 | 17 1248 | Eskimo dog, husky 1249 | 1 1250 | 250 1251 | 2 1252 | 36 1253 | malamute, malemute, Alaskan malamute 1254 | 1 1255 | 251 1256 | 2 1257 | 14 1258 | Siberian husky 1259 | 1 1260 | 252 1261 | 2 1262 | 34 1263 | dalmatian, coach dog, carriage dog 1264 | 1 1265 | 253 1266 | 2 1267 | 42 1268 | affenpinscher, monkey pinscher, monkey dog 1269 | 1 1270 | 254 1271 | 2 1272 | 7 1273 | basenji 1274 | 1 1275 | 255 1276 | 2 1277 | 12 1278 | pug, pug-dog 1279 | 1 1280 | 256 1281 | 2 1282 | 8 1283 | Leonberg 1284 | 1 1285 | 257 1286 | 2 1287 | 30 1288 | Newfoundland, Newfoundland dog 1289 | 1 1290 | 258 1291 | 2 1292 | 14 1293 | Great Pyrenees 1294 | 1 1295 | 259 1296 | 2 1297 | 17 1298 | Samoyed, Samoyede 1299 | 1 1300 | 260 1301 | 2 1302 | 10 1303 | Pomeranian 1304 | 1 1305 | 261 1306 | 2 1307 | 15 1308 | chow, chow chow 1309 | 1 1310 | 262 1311 | 2 1312 | 8 1313 | keeshond 1314 | 1 1315 | 263 1316 | 2 1317 | 17 1318 | Brabancon griffon 1319 | 1 1320 | 264 1321 | 2 1322 | 30 1323 | Pembroke, Pembroke Welsh corgi 1324 | 1 1325 | 265 1326 | 2 1327 | 30 1328 | Cardigan, Cardigan Welsh corgi 1329 | 1 1330 | 266 1331 | 2 1332 | 10 1333 | toy poodle 1334 | 1 1335 | 267 1336 | 2 1337 | 16 1338 | miniature poodle 1339 | 1 1340 | 268 1341 | 2 1342 | 15 1343 | standard poodle 1344 | 1 1345 | 269 1346 | 2 1347 | 16 1348 | Mexican hairless 1349 | 1 1350 | 270 1351 | 2 1352 | 46 1353 | timber wolf, grey wolf, gray wolf, Canis lupus 1354 | 1 1355 | 271 1356 | 2 1357 | 46 1358 | white wolf, Arctic wolf, Canis lupus tundrarum 1359 | 1 1360 | 272 1361 | 2 1362 | 46 1363 | red wolf, maned wolf, Canis rufus, Canis niger 1364 | 1 1365 | 273 1366 | 2 1367 | 47 1368 | coyote, prairie wolf, brush wolf, Canis latrans 1369 | 1 1370 | 274 1371 | 2 1372 | 38 1373 | dingo, warrigal, warragal, Canis dingo 1374 | 1 1375 | 275 1376 | 2 1377 | 19 1378 | dhole, Cuon alpinus 1379 | 1 1380 | 276 1381 | 2 1382 | 63 1383 | African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus 1384 | 1 1385 | 277 1386 | 2 1387 | 13 1388 | hyena, hyaena 1389 | 1 1390 | 278 1391 | 2 1392 | 22 1393 | red fox, Vulpes vulpes 1394 | 1 1395 | 279 1396 | 2 1397 | 24 1398 | kit fox, Vulpes macrotis 1399 | 1 1400 | 280 1401 | 2 1402 | 37 1403 | Arctic fox, white fox, Alopex lagopus 1404 | 1 1405 | 281 1406 | 2 1407 | 44 1408 | grey fox, gray fox, Urocyon cinereoargenteus 1409 | 1 1410 | 282 1411 | 2 1412 | 16 1413 | tabby, tabby cat 1414 | 1 1415 | 283 1416 | 2 1417 | 9 1418 | tiger cat 1419 | 1 1420 | 284 1421 | 2 1422 | 11 1423 | Persian cat 1424 | 1 1425 | 285 1426 | 2 1427 | 20 1428 | Siamese cat, Siamese 1429 | 1 1430 | 286 1431 | 2 1432 | 12 1433 | Egyptian cat 1434 | 1 1435 | 287 1436 | 2 1437 | 72 1438 | cougar, puma, catamount, mountain lion, painter, panther, Felis concolor 1439 | 1 1440 | 288 1441 | 2 1442 | 15 1443 | lynx, catamount 1444 | 1 1445 | 289 1446 | 2 1447 | 24 1448 | leopard, Panthera pardus 1449 | 1 1450 | 290 1451 | 2 1452 | 35 1453 | snow leopard, ounce, Panthera uncia 1454 | 1 1455 | 291 1456 | 2 1457 | 42 1458 | jaguar, panther, Panthera onca, Felis onca 1459 | 1 1460 | 292 1461 | 2 1462 | 34 1463 | lion, king of beasts, Panthera leo 1464 | 1 1465 | 293 1466 | 2 1467 | 22 1468 | tiger, Panthera tigris 1469 | 1 1470 | 294 1471 | 2 1472 | 33 1473 | cheetah, chetah, Acinonyx jubatus 1474 | 1 1475 | 295 1476 | 2 1477 | 31 1478 | brown bear, bruin, Ursus arctos 1479 | 1 1480 | 296 1481 | 2 1482 | 70 1483 | American black bear, black bear, Ursus americanus, Euarctos americanus 1484 | 1 1485 | 297 1486 | 2 1487 | 59 1488 | ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus 1489 | 1 1490 | 298 1491 | 2 1492 | 43 1493 | sloth bear, Melursus ursinus, Ursus ursinus 1494 | 1 1495 | 299 1496 | 2 1497 | 8 1498 | mongoose 1499 | 1 1500 | 300 1501 | 2 1502 | 16 1503 | meerkat, mierkat 1504 | 1 1505 | 301 1506 | 2 1507 | 12 1508 | tiger beetle 1509 | 1 1510 | 302 1511 | 2 1512 | 59 1513 | ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle 1514 | 1 1515 | 303 1516 | 2 1517 | 29 1518 | ground beetle, carabid beetle 1519 | 1 1520 | 304 1521 | 2 1522 | 47 1523 | long-horned beetle, longicorn, longicorn beetle 1524 | 1 1525 | 305 1526 | 2 1527 | 24 1528 | leaf beetle, chrysomelid 1529 | 1 1530 | 306 1531 | 2 1532 | 11 1533 | dung beetle 1534 | 1 1535 | 307 1536 | 2 1537 | 17 1538 | rhinoceros beetle 1539 | 1 1540 | 308 1541 | 2 1542 | 6 1543 | weevil 1544 | 1 1545 | 309 1546 | 2 1547 | 3 1548 | fly 1549 | 1 1550 | 310 1551 | 2 1552 | 3 1553 | bee 1554 | 1 1555 | 311 1556 | 2 1557 | 19 1558 | ant, emmet, pismire 1559 | 1 1560 | 312 1561 | 2 1562 | 19 1563 | grasshopper, hopper 1564 | 1 1565 | 313 1566 | 2 1567 | 7 1568 | cricket 1569 | 1 1570 | 314 1571 | 2 1572 | 41 1573 | walking stick, walkingstick, stick insect 1574 | 1 1575 | 315 1576 | 2 1577 | 16 1578 | cockroach, roach 1579 | 1 1580 | 316 1581 | 2 1582 | 14 1583 | mantis, mantid 1584 | 1 1585 | 317 1586 | 2 1587 | 14 1588 | cicada, cicala 1589 | 1 1590 | 318 1591 | 2 1592 | 10 1593 | leafhopper 1594 | 1 1595 | 319 1596 | 2 1597 | 22 1598 | lacewing, lacewing fly 1599 | 1 1600 | 320 1601 | 2 1602 | 121 1603 | dragonfly, darning needle, devil's darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk 1604 | 1 1605 | 321 1606 | 2 1607 | 9 1608 | damselfly 1609 | 1 1610 | 322 1611 | 2 1612 | 7 1613 | admiral 1614 | 1 1615 | 323 1616 | 2 1617 | 26 1618 | ringlet, ringlet butterfly 1619 | 1 1620 | 324 1621 | 2 1622 | 64 1623 | monarch, monarch butterfly, milkweed butterfly, Danaus plexippus 1624 | 1 1625 | 325 1626 | 2 1627 | 17 1628 | cabbage butterfly 1629 | 1 1630 | 326 1631 | 2 1632 | 35 1633 | sulphur butterfly, sulfur butterfly 1634 | 1 1635 | 327 1636 | 2 1637 | 28 1638 | lycaenid, lycaenid butterfly 1639 | 1 1640 | 328 1641 | 2 1642 | 18 1643 | starfish, sea star 1644 | 1 1645 | 329 1646 | 2 1647 | 10 1648 | sea urchin 1649 | 1 1650 | 330 1651 | 2 1652 | 25 1653 | sea cucumber, holothurian 1654 | 1 1655 | 331 1656 | 2 1657 | 42 1658 | wood rabbit, cottontail, cottontail rabbit 1659 | 1 1660 | 332 1661 | 2 1662 | 4 1663 | hare 1664 | 1 1665 | 333 1666 | 2 1667 | 21 1668 | Angora, Angora rabbit 1669 | 1 1670 | 334 1671 | 2 1672 | 7 1673 | hamster 1674 | 1 1675 | 335 1676 | 2 1677 | 19 1678 | porcupine, hedgehog 1679 | 1 1680 | 336 1681 | 2 1682 | 49 1683 | fox squirrel, eastern fox squirrel, Sciurus niger 1684 | 1 1685 | 337 1686 | 2 1687 | 6 1688 | marmot 1689 | 1 1690 | 338 1691 | 2 1692 | 6 1693 | beaver 1694 | 1 1695 | 339 1696 | 2 1697 | 24 1698 | guinea pig, Cavia cobaya 1699 | 1 1700 | 340 1701 | 2 1702 | 6 1703 | sorrel 1704 | 1 1705 | 341 1706 | 2 1707 | 5 1708 | zebra 1709 | 1 1710 | 342 1711 | 2 1712 | 39 1713 | hog, pig, grunter, squealer, Sus scrofa 1714 | 1 1715 | 343 1716 | 2 1717 | 27 1718 | wild boar, boar, Sus scrofa 1719 | 1 1720 | 344 1721 | 2 1722 | 7 1723 | warthog 1724 | 1 1725 | 345 1726 | 2 1727 | 56 1728 | hippopotamus, hippo, river horse, Hippopotamus amphibius 1729 | 1 1730 | 346 1731 | 2 1732 | 2 1733 | ox 1734 | 1 1735 | 347 1736 | 2 1737 | 57 1738 | water buffalo, water ox, Asiatic buffalo, Bubalus bubalis 1739 | 1 1740 | 348 1741 | 2 1742 | 5 1743 | bison 1744 | 1 1745 | 349 1746 | 2 1747 | 8 1748 | ram, tup 1749 | 1 1750 | 350 1751 | 2 1752 | 95 1753 | bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis 1754 | 1 1755 | 351 1756 | 2 1757 | 16 1758 | ibex, Capra ibex 1759 | 1 1760 | 352 1761 | 2 1762 | 10 1763 | hartebeest 1764 | 1 1765 | 353 1766 | 2 1767 | 26 1768 | impala, Aepyceros melampus 1769 | 1 1770 | 354 1771 | 2 1772 | 7 1773 | gazelle 1774 | 1 1775 | 355 1776 | 2 1777 | 45 1778 | Arabian camel, dromedary, Camelus dromedarius 1779 | 1 1780 | 356 1781 | 2 1782 | 5 1783 | llama 1784 | 1 1785 | 357 1786 | 2 1787 | 6 1788 | weasel 1789 | 1 1790 | 358 1791 | 2 1792 | 4 1793 | mink 1794 | 1 1795 | 359 1796 | 2 1797 | 51 1798 | polecat, fitch, foulmart, foumart, Mustela putorius 1799 | 1 1800 | 360 1801 | 2 1802 | 45 1803 | black-footed ferret, ferret, Mustela nigripes 1804 | 1 1805 | 361 1806 | 2 1807 | 5 1808 | otter 1809 | 1 1810 | 362 1811 | 2 1812 | 26 1813 | skunk, polecat, wood pussy 1814 | 1 1815 | 363 1816 | 2 1817 | 6 1818 | badger 1819 | 1 1820 | 364 1821 | 2 1822 | 9 1823 | armadillo 1824 | 1 1825 | 365 1826 | 2 1827 | 42 1828 | three-toed sloth, ai, Bradypus tridactylus 1829 | 1 1830 | 366 1831 | 2 1832 | 44 1833 | orangutan, orang, orangutang, Pongo pygmaeus 1834 | 1 1835 | 367 1836 | 2 1837 | 24 1838 | gorilla, Gorilla gorilla 1839 | 1 1840 | 368 1841 | 2 1842 | 34 1843 | chimpanzee, chimp, Pan troglodytes 1844 | 1 1845 | 369 1846 | 2 1847 | 21 1848 | gibbon, Hylobates lar 1849 | 1 1850 | 370 1851 | 2 1852 | 56 1853 | siamang, Hylobates syndactylus, Symphalangus syndactylus 1854 | 1 1855 | 371 1856 | 2 1857 | 21 1858 | guenon, guenon monkey 1859 | 1 1860 | 372 1861 | 2 1862 | 40 1863 | patas, hussar monkey, Erythrocebus patas 1864 | 1 1865 | 373 1866 | 2 1867 | 6 1868 | baboon 1869 | 1 1870 | 374 1871 | 2 1872 | 7 1873 | macaque 1874 | 1 1875 | 375 1876 | 2 1877 | 6 1878 | langur 1879 | 1 1880 | 376 1881 | 2 1882 | 23 1883 | colobus, colobus monkey 1884 | 1 1885 | 377 1886 | 2 1887 | 34 1888 | proboscis monkey, Nasalis larvatus 1889 | 1 1890 | 378 1891 | 2 1892 | 8 1893 | marmoset 1894 | 1 1895 | 379 1896 | 2 1897 | 35 1898 | capuchin, ringtail, Cebus capucinus 1899 | 1 1900 | 380 1901 | 2 1902 | 21 1903 | howler monkey, howler 1904 | 1 1905 | 381 1906 | 2 1907 | 17 1908 | titi, titi monkey 1909 | 1 1910 | 382 1911 | 2 1912 | 31 1913 | spider monkey, Ateles geoffroyi 1914 | 1 1915 | 383 1916 | 2 1917 | 33 1918 | squirrel monkey, Saimiri sciureus 1919 | 1 1920 | 384 1921 | 2 1922 | 46 1923 | Madagascar cat, ring-tailed lemur, Lemur catta 1924 | 1 1925 | 385 1926 | 2 1927 | 47 1928 | indri, indris, Indri indri, Indri brevicaudatus 1929 | 1 1930 | 386 1931 | 2 1932 | 32 1933 | Indian elephant, Elephas maximus 1934 | 1 1935 | 387 1936 | 2 1937 | 36 1938 | African elephant, Loxodonta africana 1939 | 1 1940 | 388 1941 | 2 1942 | 67 1943 | lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens 1944 | 1 1945 | 389 1946 | 2 1947 | 65 1948 | giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca 1949 | 1 1950 | 390 1951 | 2 1952 | 17 1953 | barracouta, snoek 1954 | 1 1955 | 391 1956 | 2 1957 | 3 1958 | eel 1959 | 1 1960 | 392 1961 | 2 1962 | 72 1963 | coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch 1964 | 1 1965 | 393 1966 | 2 1967 | 33 1968 | rock beauty, Holocanthus tricolor 1969 | 1 1970 | 394 1971 | 2 1972 | 12 1973 | anemone fish 1974 | 1 1975 | 395 1976 | 2 1977 | 8 1978 | sturgeon 1979 | 1 1980 | 396 1981 | 2 1982 | 51 1983 | gar, garfish, garpike, billfish, Lepisosteus osseus 1984 | 1 1985 | 397 1986 | 2 1987 | 8 1988 | lionfish 1989 | 1 1990 | 398 1991 | 2 1992 | 39 1993 | puffer, pufferfish, blowfish, globefish 1994 | 1 1995 | 399 1996 | 2 1997 | 6 1998 | abacus 1999 | 1 2000 | 400 2001 | 2 2002 | 5 2003 | abaya 2004 | 1 2005 | 401 2006 | 2 2007 | 42 2008 | academic gown, academic robe, judge's robe 2009 | 1 2010 | 402 2011 | 2 2012 | 39 2013 | accordion, piano accordion, squeeze box 2014 | 1 2015 | 403 2016 | 2 2017 | 15 2018 | acoustic guitar 2019 | 1 2020 | 404 2021 | 2 2022 | 59 2023 | aircraft carrier, carrier, flattop, attack aircraft carrier 2024 | 1 2025 | 405 2026 | 2 2027 | 8 2028 | airliner 2029 | 1 2030 | 406 2031 | 2 2032 | 18 2033 | airship, dirigible 2034 | 1 2035 | 407 2036 | 2 2037 | 5 2038 | altar 2039 | 1 2040 | 408 2041 | 2 2042 | 9 2043 | ambulance 2044 | 1 2045 | 409 2046 | 2 2047 | 29 2048 | amphibian, amphibious vehicle 2049 | 1 2050 | 410 2051 | 2 2052 | 12 2053 | analog clock 2054 | 1 2055 | 411 2056 | 2 2057 | 17 2058 | apiary, bee house 2059 | 1 2060 | 412 2061 | 2 2062 | 5 2063 | apron 2064 | 1 2065 | 413 2066 | 2 2067 | 100 2068 | ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin 2069 | 1 2070 | 414 2071 | 2 2072 | 26 2073 | assault rifle, assault gun 2074 | 1 2075 | 415 2076 | 2 2077 | 60 2078 | backpack, back pack, knapsack, packsack, rucksack, haversack 2079 | 1 2080 | 416 2081 | 2 2082 | 27 2083 | bakery, bakeshop, bakehouse 2084 | 1 2085 | 417 2086 | 2 2087 | 18 2088 | balance beam, beam 2089 | 1 2090 | 418 2091 | 2 2092 | 7 2093 | balloon 2094 | 1 2095 | 419 2096 | 2 2097 | 39 2098 | ballpoint, ballpoint pen, ballpen, Biro 2099 | 1 2100 | 420 2101 | 2 2102 | 8 2103 | Band Aid 2104 | 1 2105 | 421 2106 | 2 2107 | 5 2108 | banjo 2109 | 1 2110 | 422 2111 | 2 2112 | 52 2113 | bannister, banister, balustrade, balusters, handrail 2114 | 1 2115 | 423 2116 | 2 2117 | 7 2118 | barbell 2119 | 1 2120 | 424 2121 | 2 2122 | 12 2123 | barber chair 2124 | 1 2125 | 425 2126 | 2 2127 | 10 2128 | barbershop 2129 | 1 2130 | 426 2131 | 2 2132 | 4 2133 | barn 2134 | 1 2135 | 427 2136 | 2 2137 | 9 2138 | barometer 2139 | 1 2140 | 428 2141 | 2 2142 | 12 2143 | barrel, cask 2144 | 1 2145 | 429 2146 | 2 2147 | 43 2148 | barrow, garden cart, lawn cart, wheelbarrow 2149 | 1 2150 | 430 2151 | 2 2152 | 8 2153 | baseball 2154 | 1 2155 | 431 2156 | 2 2157 | 10 2158 | basketball 2159 | 1 2160 | 432 2161 | 2 2162 | 8 2163 | bassinet 2164 | 1 2165 | 433 2166 | 2 2167 | 7 2168 | bassoon 2169 | 1 2170 | 434 2171 | 2 2172 | 25 2173 | bathing cap, swimming cap 2174 | 1 2175 | 435 2176 | 2 2177 | 10 2178 | bath towel 2179 | 1 2180 | 436 2181 | 2 2182 | 31 2183 | bathtub, bathing tub, bath, tub 2184 | 1 2185 | 437 2186 | 2 2187 | 83 2188 | beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon 2189 | 1 2190 | 438 2191 | 2 2192 | 40 2193 | beacon, lighthouse, beacon light, pharos 2194 | 1 2195 | 439 2196 | 2 2197 | 6 2198 | beaker 2199 | 1 2200 | 440 2201 | 2 2202 | 22 2203 | bearskin, busby, shako 2204 | 1 2205 | 441 2206 | 2 2207 | 11 2208 | beer bottle 2209 | 1 2210 | 442 2211 | 2 2212 | 10 2213 | beer glass 2214 | 1 2215 | 443 2216 | 2 2217 | 19 2218 | bell cote, bell cot 2219 | 1 2220 | 444 2221 | 2 2222 | 3 2223 | bib 2224 | 1 2225 | 445 2226 | 2 2227 | 45 2228 | bicycle-built-for-two, tandem bicycle, tandem 2229 | 1 2230 | 446 2231 | 2 2232 | 17 2233 | bikini, two-piece 2234 | 1 2235 | 447 2236 | 2 2237 | 19 2238 | binder, ring-binder 2239 | 1 2240 | 448 2241 | 2 2242 | 40 2243 | binoculars, field glasses, opera glasses 2244 | 1 2245 | 449 2246 | 2 2247 | 9 2248 | birdhouse 2249 | 1 2250 | 450 2251 | 2 2252 | 9 2253 | boathouse 2254 | 1 2255 | 451 2256 | 2 2257 | 23 2258 | bobsled, bobsleigh, bob 2259 | 1 2260 | 452 2261 | 2 2262 | 30 2263 | bolo tie, bolo, bola tie, bola 2264 | 1 2265 | 453 2266 | 2 2267 | 19 2268 | bonnet, poke bonnet 2269 | 1 2270 | 454 2271 | 2 2272 | 8 2273 | bookcase 2274 | 1 2275 | 455 2276 | 2 2277 | 30 2278 | bookshop, bookstore, bookstall 2279 | 1 2280 | 456 2281 | 2 2282 | 9 2283 | bottlecap 2284 | 1 2285 | 457 2286 | 2 2287 | 3 2288 | bow 2289 | 1 2290 | 458 2291 | 2 2292 | 24 2293 | bow tie, bow-tie, bowtie 2294 | 1 2295 | 459 2296 | 2 2297 | 30 2298 | brass, memorial tablet, plaque 2299 | 1 2300 | 460 2301 | 2 2302 | 23 2303 | brassiere, bra, bandeau 2304 | 1 2305 | 461 2306 | 2 2307 | 56 2308 | breakwater, groin, groyne, mole, bulwark, seawall, jetty 2309 | 1 2310 | 462 2311 | 2 2312 | 24 2313 | breastplate, aegis, egis 2314 | 1 2315 | 463 2316 | 2 2317 | 5 2318 | broom 2319 | 1 2320 | 464 2321 | 2 2322 | 12 2323 | bucket, pail 2324 | 1 2325 | 465 2326 | 2 2327 | 6 2328 | buckle 2329 | 1 2330 | 466 2331 | 2 2332 | 16 2333 | bulletproof vest 2334 | 1 2335 | 467 2336 | 2 2337 | 20 2338 | bullet train, bullet 2339 | 1 2340 | 468 2341 | 2 2342 | 25 2343 | butcher shop, meat market 2344 | 1 2345 | 469 2346 | 2 2347 | 24 2348 | cab, hack, taxi, taxicab 2349 | 1 2350 | 470 2351 | 2 2352 | 17 2353 | caldron, cauldron 2354 | 1 2355 | 471 2356 | 2 2357 | 24 2358 | candle, taper, wax light 2359 | 1 2360 | 472 2361 | 2 2362 | 6 2363 | cannon 2364 | 1 2365 | 473 2366 | 2 2367 | 5 2368 | canoe 2369 | 1 2370 | 474 2371 | 2 2372 | 22 2373 | can opener, tin opener 2374 | 1 2375 | 475 2376 | 2 2377 | 8 2378 | cardigan 2379 | 1 2380 | 476 2381 | 2 2382 | 10 2383 | car mirror 2384 | 1 2385 | 477 2386 | 2 2387 | 58 2388 | carousel, carrousel, merry-go-round, roundabout, whirligig 2389 | 1 2390 | 478 2391 | 2 2392 | 25 2393 | carpenter's kit, tool kit 2394 | 1 2395 | 479 2396 | 2 2397 | 6 2398 | carton 2399 | 1 2400 | 480 2401 | 2 2402 | 9 2403 | car wheel 2404 | 1 2405 | 481 2406 | 2 2407 | 121 2408 | cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM 2409 | 1 2410 | 482 2411 | 2 2412 | 8 2413 | cassette 2414 | 1 2415 | 483 2416 | 2 2417 | 15 2418 | cassette player 2419 | 1 2420 | 484 2421 | 2 2422 | 6 2423 | castle 2424 | 1 2425 | 485 2426 | 2 2427 | 9 2428 | catamaran 2429 | 1 2430 | 486 2431 | 2 2432 | 9 2433 | CD player 2434 | 1 2435 | 487 2436 | 2 2437 | 18 2438 | cello, violoncello 2439 | 1 2440 | 488 2441 | 2 2442 | 65 2443 | cellular telephone, cellular phone, cellphone, cell, mobile phone 2444 | 1 2445 | 489 2446 | 2 2447 | 5 2448 | chain 2449 | 1 2450 | 490 2451 | 2 2452 | 15 2453 | chainlink fence 2454 | 1 2455 | 491 2456 | 2 2457 | 79 2458 | chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour 2459 | 1 2460 | 492 2461 | 2 2462 | 19 2463 | chain saw, chainsaw 2464 | 1 2465 | 493 2466 | 2 2467 | 5 2468 | chest 2469 | 1 2470 | 494 2471 | 2 2472 | 19 2473 | chiffonier, commode 2474 | 1 2475 | 495 2476 | 2 2477 | 17 2478 | chime, bell, gong 2479 | 1 2480 | 496 2481 | 2 2482 | 27 2483 | china cabinet, china closet 2484 | 1 2485 | 497 2486 | 2 2487 | 18 2488 | Christmas stocking 2489 | 1 2490 | 498 2491 | 2 2492 | 23 2493 | church, church building 2494 | 1 2495 | 499 2496 | 2 2497 | 65 2498 | cinema, movie theater, movie theatre, movie house, picture palace 2499 | 1 2500 | 500 2501 | 2 2502 | 30 2503 | cleaver, meat cleaver, chopper 2504 | 1 2505 | 501 2506 | 2 2507 | 14 2508 | cliff dwelling 2509 | 1 2510 | 502 2511 | 2 2512 | 5 2513 | cloak 2514 | 1 2515 | 503 2516 | 2 2517 | 25 2518 | clog, geta, patten, sabot 2519 | 1 2520 | 504 2521 | 2 2522 | 15 2523 | cocktail shaker 2524 | 1 2525 | 505 2526 | 2 2527 | 10 2528 | coffee mug 2529 | 1 2530 | 506 2531 | 2 2532 | 9 2533 | coffeepot 2534 | 1 2535 | 507 2536 | 2 2537 | 34 2538 | coil, spiral, volute, whorl, helix 2539 | 1 2540 | 508 2541 | 2 2542 | 16 2543 | combination lock 2544 | 1 2545 | 509 2546 | 2 2547 | 25 2548 | computer keyboard, keypad 2549 | 1 2550 | 510 2551 | 2 2552 | 41 2553 | confectionery, confectionary, candy store 2554 | 1 2555 | 511 2556 | 2 2557 | 47 2558 | container ship, containership, container vessel 2559 | 1 2560 | 512 2561 | 2 2562 | 11 2563 | convertible 2564 | 1 2565 | 513 2566 | 2 2567 | 23 2568 | corkscrew, bottle screw 2569 | 1 2570 | 514 2571 | 2 2572 | 28 2573 | cornet, horn, trumpet, trump 2574 | 1 2575 | 515 2576 | 2 2577 | 11 2578 | cowboy boot 2579 | 1 2580 | 516 2581 | 2 2582 | 26 2583 | cowboy hat, ten-gallon hat 2584 | 1 2585 | 517 2586 | 2 2587 | 6 2588 | cradle 2589 | 1 2590 | 518 2591 | 2 2592 | 5 2593 | crane 2594 | 1 2595 | 519 2596 | 2 2597 | 12 2598 | crash helmet 2599 | 1 2600 | 520 2601 | 2 2602 | 5 2603 | crate 2604 | 1 2605 | 521 2606 | 2 2607 | 9 2608 | crib, cot 2609 | 1 2610 | 522 2611 | 2 2612 | 9 2613 | Crock Pot 2614 | 1 2615 | 523 2616 | 2 2617 | 12 2618 | croquet ball 2619 | 1 2620 | 524 2621 | 2 2622 | 6 2623 | crutch 2624 | 1 2625 | 525 2626 | 2 2627 | 7 2628 | cuirass 2629 | 1 2630 | 526 2631 | 2 2632 | 15 2633 | dam, dike, dyke 2634 | 1 2635 | 527 2636 | 2 2637 | 4 2638 | desk 2639 | 1 2640 | 528 2641 | 2 2642 | 16 2643 | desktop computer 2644 | 1 2645 | 529 2646 | 2 2647 | 26 2648 | dial telephone, dial phone 2649 | 1 2650 | 530 2651 | 2 2652 | 21 2653 | diaper, nappy, napkin 2654 | 1 2655 | 531 2656 | 2 2657 | 13 2658 | digital clock 2659 | 1 2660 | 532 2661 | 2 2662 | 13 2663 | digital watch 2664 | 1 2665 | 533 2666 | 2 2667 | 19 2668 | dining table, board 2669 | 1 2670 | 534 2671 | 2 2672 | 18 2673 | dishrag, dishcloth 2674 | 1 2675 | 535 2676 | 2 2677 | 44 2678 | dishwasher, dish washer, dishwashing machine 2679 | 1 2680 | 536 2681 | 2 2682 | 22 2683 | disk brake, disc brake 2684 | 1 2685 | 537 2686 | 2 2687 | 31 2688 | dock, dockage, docking facility 2689 | 1 2690 | 538 2691 | 2 2692 | 29 2693 | dogsled, dog sled, dog sleigh 2694 | 1 2695 | 539 2696 | 2 2697 | 4 2698 | dome 2699 | 1 2700 | 540 2701 | 2 2702 | 20 2703 | doormat, welcome mat 2704 | 1 2705 | 541 2706 | 2 2707 | 31 2708 | drilling platform, offshore rig 2709 | 1 2710 | 542 2711 | 2 2712 | 27 2713 | drum, membranophone, tympan 2714 | 1 2715 | 543 2716 | 2 2717 | 9 2718 | drumstick 2719 | 1 2720 | 544 2721 | 2 2722 | 8 2723 | dumbbell 2724 | 1 2725 | 545 2726 | 2 2727 | 10 2728 | Dutch oven 2729 | 1 2730 | 546 2731 | 2 2732 | 20 2733 | electric fan, blower 2734 | 1 2735 | 547 2736 | 2 2737 | 15 2738 | electric guitar 2739 | 1 2740 | 548 2741 | 2 2742 | 19 2743 | electric locomotive 2744 | 1 2745 | 549 2746 | 2 2747 | 20 2748 | entertainment center 2749 | 1 2750 | 550 2751 | 2 2752 | 8 2753 | envelope 2754 | 1 2755 | 551 2756 | 2 2757 | 14 2758 | espresso maker 2759 | 1 2760 | 552 2761 | 2 2762 | 11 2763 | face powder 2764 | 1 2765 | 553 2766 | 2 2767 | 16 2768 | feather boa, boa 2769 | 1 2770 | 554 2771 | 2 2772 | 34 2773 | file, file cabinet, filing cabinet 2774 | 1 2775 | 555 2776 | 2 2777 | 8 2778 | fireboat 2779 | 1 2780 | 556 2781 | 2 2782 | 23 2783 | fire engine, fire truck 2784 | 1 2785 | 557 2786 | 2 2787 | 22 2788 | fire screen, fireguard 2789 | 1 2790 | 558 2791 | 2 2792 | 19 2793 | flagpole, flagstaff 2794 | 1 2795 | 559 2796 | 2 2797 | 23 2798 | flute, transverse flute 2799 | 1 2800 | 560 2801 | 2 2802 | 13 2803 | folding chair 2804 | 1 2805 | 561 2806 | 2 2807 | 15 2808 | football helmet 2809 | 1 2810 | 562 2811 | 2 2812 | 8 2813 | forklift 2814 | 1 2815 | 563 2816 | 2 2817 | 8 2818 | fountain 2819 | 1 2820 | 564 2821 | 2 2822 | 12 2823 | fountain pen 2824 | 1 2825 | 565 2826 | 2 2827 | 11 2828 | four-poster 2829 | 1 2830 | 566 2831 | 2 2832 | 11 2833 | freight car 2834 | 1 2835 | 567 2836 | 2 2837 | 17 2838 | French horn, horn 2839 | 1 2840 | 568 2841 | 2 2842 | 27 2843 | frying pan, frypan, skillet 2844 | 1 2845 | 569 2846 | 2 2847 | 8 2848 | fur coat 2849 | 1 2850 | 570 2851 | 2 2852 | 23 2853 | garbage truck, dustcart 2854 | 1 2855 | 571 2856 | 2 2857 | 31 2858 | gasmask, respirator, gas helmet 2859 | 1 2860 | 572 2861 | 2 2862 | 54 2863 | gas pump, gasoline pump, petrol pump, island dispenser 2864 | 1 2865 | 573 2866 | 2 2867 | 6 2868 | goblet 2869 | 1 2870 | 574 2871 | 2 2872 | 7 2873 | go-kart 2874 | 1 2875 | 575 2876 | 2 2877 | 9 2878 | golf ball 2879 | 1 2880 | 576 2881 | 2 2882 | 19 2883 | golfcart, golf cart 2884 | 1 2885 | 577 2886 | 2 2887 | 7 2888 | gondola 2889 | 1 2890 | 578 2891 | 2 2892 | 13 2893 | gong, tam-tam 2894 | 1 2895 | 579 2896 | 2 2897 | 4 2898 | gown 2899 | 1 2900 | 580 2901 | 2 2902 | 18 2903 | grand piano, grand 2904 | 1 2905 | 581 2906 | 2 2907 | 31 2908 | greenhouse, nursery, glasshouse 2909 | 1 2910 | 582 2911 | 2 2912 | 23 2913 | grille, radiator grille 2914 | 1 2915 | 583 2916 | 2 2917 | 43 2918 | grocery store, grocery, food market, market 2919 | 1 2920 | 584 2921 | 2 2922 | 10 2923 | guillotine 2924 | 1 2925 | 585 2926 | 2 2927 | 10 2928 | hair slide 2929 | 1 2930 | 586 2931 | 2 2932 | 10 2933 | hair spray 2934 | 1 2935 | 587 2936 | 2 2937 | 10 2938 | half track 2939 | 1 2940 | 588 2941 | 2 2942 | 6 2943 | hammer 2944 | 1 2945 | 589 2946 | 2 2947 | 6 2948 | hamper 2949 | 1 2950 | 590 2951 | 2 2952 | 59 2953 | hand blower, blow dryer, blow drier, hair dryer, hair drier 2954 | 1 2955 | 591 2956 | 2 2957 | 43 2958 | hand-held computer, hand-held microcomputer 2959 | 1 2960 | 592 2961 | 2 2962 | 35 2963 | handkerchief, hankie, hanky, hankey 2964 | 1 2965 | 593 2966 | 2 2967 | 32 2968 | hard disc, hard disk, fixed disk 2969 | 1 2970 | 594 2971 | 2 2972 | 40 2973 | harmonica, mouth organ, harp, mouth harp 2974 | 1 2975 | 595 2976 | 2 2977 | 4 2978 | harp 2979 | 1 2980 | 596 2981 | 2 2982 | 17 2983 | harvester, reaper 2984 | 1 2985 | 597 2986 | 2 2987 | 7 2988 | hatchet 2989 | 1 2990 | 598 2991 | 2 2992 | 7 2993 | holster 2994 | 1 2995 | 599 2996 | 2 2997 | 26 2998 | home theater, home theatre 2999 | 1 3000 | 600 3001 | 2 3002 | 9 3003 | honeycomb 3004 | 1 3005 | 601 3006 | 2 3007 | 10 3008 | hook, claw 3009 | 1 3010 | 602 3011 | 2 3012 | 20 3013 | hoopskirt, crinoline 3014 | 1 3015 | 603 3016 | 2 3017 | 24 3018 | horizontal bar, high bar 3019 | 1 3020 | 604 3021 | 2 3022 | 22 3023 | horse cart, horse-cart 3024 | 1 3025 | 605 3026 | 2 3027 | 9 3028 | hourglass 3029 | 1 3030 | 606 3031 | 2 3032 | 4 3033 | iPod 3034 | 1 3035 | 607 3036 | 2 3037 | 20 3038 | iron, smoothing iron 3039 | 1 3040 | 608 3041 | 2 3042 | 15 3043 | jack-o'-lantern 3044 | 1 3045 | 609 3046 | 2 3047 | 22 3048 | jean, blue jean, denim 3049 | 1 3050 | 610 3051 | 2 3052 | 15 3053 | jeep, landrover 3054 | 1 3055 | 611 3056 | 2 3057 | 26 3058 | jersey, T-shirt, tee shirt 3059 | 1 3060 | 612 3061 | 2 3062 | 13 3063 | jigsaw puzzle 3064 | 1 3065 | 613 3066 | 2 3067 | 29 3068 | jinrikisha, ricksha, rickshaw 3069 | 1 3070 | 614 3071 | 2 3072 | 8 3073 | joystick 3074 | 1 3075 | 615 3076 | 2 3077 | 6 3078 | kimono 3079 | 1 3080 | 616 3081 | 2 3082 | 8 3083 | knee pad 3084 | 1 3085 | 617 3086 | 2 3087 | 4 3088 | knot 3089 | 1 3090 | 618 3091 | 2 3092 | 25 3093 | lab coat, laboratory coat 3094 | 1 3095 | 619 3096 | 2 3097 | 5 3098 | ladle 3099 | 1 3100 | 620 3101 | 2 3102 | 21 3103 | lampshade, lamp shade 3104 | 1 3105 | 621 3106 | 2 3107 | 23 3108 | laptop, laptop computer 3109 | 1 3110 | 622 3111 | 2 3112 | 17 3113 | lawn mower, mower 3114 | 1 3115 | 623 3116 | 2 3117 | 20 3118 | lens cap, lens cover 3119 | 1 3120 | 624 3121 | 2 3122 | 38 3123 | letter opener, paper knife, paperknife 3124 | 1 3125 | 625 3126 | 2 3127 | 7 3128 | library 3129 | 1 3130 | 626 3131 | 2 3132 | 8 3133 | lifeboat 3134 | 1 3135 | 627 3136 | 2 3137 | 32 3138 | lighter, light, igniter, ignitor 3139 | 1 3140 | 628 3141 | 2 3142 | 15 3143 | limousine, limo 3144 | 1 3145 | 629 3146 | 2 3147 | 18 3148 | liner, ocean liner 3149 | 1 3150 | 630 3151 | 2 3152 | 19 3153 | lipstick, lip rouge 3154 | 1 3155 | 631 3156 | 2 3157 | 6 3158 | Loafer 3159 | 1 3160 | 632 3161 | 2 3162 | 6 3163 | lotion 3164 | 1 3165 | 633 3166 | 2 3167 | 70 3168 | loudspeaker, speaker, speaker unit, loudspeaker system, speaker system 3169 | 1 3170 | 634 3171 | 2 3172 | 22 3173 | loupe, jeweler's loupe 3174 | 1 3175 | 635 3176 | 2 3177 | 19 3178 | lumbermill, sawmill 3179 | 1 3180 | 636 3181 | 2 3182 | 16 3183 | magnetic compass 3184 | 1 3185 | 637 3186 | 2 3187 | 16 3188 | mailbag, postbag 3189 | 1 3190 | 638 3191 | 2 3192 | 19 3193 | mailbox, letter box 3194 | 1 3195 | 639 3196 | 2 3197 | 7 3198 | maillot 3199 | 1 3200 | 640 3201 | 2 3202 | 18 3203 | maillot, tank suit 3204 | 1 3205 | 641 3206 | 2 3207 | 13 3208 | manhole cover 3209 | 1 3210 | 642 3211 | 2 3212 | 6 3213 | maraca 3214 | 1 3215 | 643 3216 | 2 3217 | 18 3218 | marimba, xylophone 3219 | 1 3220 | 644 3221 | 2 3222 | 4 3223 | mask 3224 | 1 3225 | 645 3226 | 2 3227 | 10 3228 | matchstick 3229 | 1 3230 | 646 3231 | 2 3232 | 7 3233 | maypole 3234 | 1 3235 | 647 3236 | 2 3237 | 15 3238 | maze, labyrinth 3239 | 1 3240 | 648 3241 | 2 3242 | 13 3243 | measuring cup 3244 | 1 3245 | 649 3246 | 2 3247 | 32 3248 | medicine chest, medicine cabinet 3249 | 1 3250 | 650 3251 | 2 3252 | 30 3253 | megalith, megalithic structure 3254 | 1 3255 | 651 3256 | 2 3257 | 16 3258 | microphone, mike 3259 | 1 3260 | 652 3261 | 2 3262 | 25 3263 | microwave, microwave oven 3264 | 1 3265 | 653 3266 | 2 3267 | 16 3268 | military uniform 3269 | 1 3270 | 654 3271 | 2 3272 | 8 3273 | milk can 3274 | 1 3275 | 655 3276 | 2 3277 | 7 3278 | minibus 3279 | 1 3280 | 656 3281 | 2 3282 | 15 3283 | miniskirt, mini 3284 | 1 3285 | 657 3286 | 2 3287 | 7 3288 | minivan 3289 | 1 3290 | 658 3291 | 2 3292 | 7 3293 | missile 3294 | 1 3295 | 659 3296 | 2 3297 | 6 3298 | mitten 3299 | 1 3300 | 660 3301 | 2 3302 | 11 3303 | mixing bowl 3304 | 1 3305 | 661 3306 | 2 3307 | 30 3308 | mobile home, manufactured home 3309 | 1 3310 | 662 3311 | 2 3312 | 7 3313 | Model T 3314 | 1 3315 | 663 3316 | 2 3317 | 5 3318 | modem 3319 | 1 3320 | 664 3321 | 2 3322 | 9 3323 | monastery 3324 | 1 3325 | 665 3326 | 2 3327 | 7 3328 | monitor 3329 | 1 3330 | 666 3331 | 2 3332 | 5 3333 | moped 3334 | 1 3335 | 667 3336 | 2 3337 | 6 3338 | mortar 3339 | 1 3340 | 668 3341 | 2 3342 | 11 3343 | mortarboard 3344 | 1 3345 | 669 3346 | 2 3347 | 6 3348 | mosque 3349 | 1 3350 | 670 3351 | 2 3352 | 12 3353 | mosquito net 3354 | 1 3355 | 671 3356 | 2 3357 | 22 3358 | motor scooter, scooter 3359 | 1 3360 | 672 3361 | 2 3362 | 43 3363 | mountain bike, all-terrain bike, off-roader 3364 | 1 3365 | 673 3366 | 2 3367 | 13 3368 | mountain tent 3369 | 1 3370 | 674 3371 | 2 3372 | 21 3373 | mouse, computer mouse 3374 | 1 3375 | 675 3376 | 2 3377 | 9 3378 | mousetrap 3379 | 1 3380 | 676 3381 | 2 3382 | 10 3383 | moving van 3384 | 1 3385 | 677 3386 | 2 3387 | 6 3388 | muzzle 3389 | 1 3390 | 678 3391 | 2 3392 | 4 3393 | nail 3394 | 1 3395 | 679 3396 | 2 3397 | 10 3398 | neck brace 3399 | 1 3400 | 680 3401 | 2 3402 | 8 3403 | necklace 3404 | 1 3405 | 681 3406 | 2 3407 | 6 3408 | nipple 3409 | 1 3410 | 682 3411 | 2 3412 | 27 3413 | notebook, notebook computer 3414 | 1 3415 | 683 3416 | 2 3417 | 7 3418 | obelisk 3419 | 1 3420 | 684 3421 | 2 3422 | 23 3423 | oboe, hautboy, hautbois 3424 | 1 3425 | 685 3426 | 2 3427 | 21 3428 | ocarina, sweet potato 3429 | 1 3430 | 686 3431 | 2 3432 | 42 3433 | odometer, hodometer, mileometer, milometer 3434 | 1 3435 | 687 3436 | 2 3437 | 10 3438 | oil filter 3439 | 1 3440 | 688 3441 | 2 3442 | 17 3443 | organ, pipe organ 3444 | 1 3445 | 689 3446 | 2 3447 | 50 3448 | oscilloscope, scope, cathode-ray oscilloscope, CRO 3449 | 1 3450 | 690 3451 | 2 3452 | 9 3453 | overskirt 3454 | 1 3455 | 691 3456 | 2 3457 | 6 3458 | oxcart 3459 | 1 3460 | 692 3461 | 2 3462 | 11 3463 | oxygen mask 3464 | 1 3465 | 693 3466 | 2 3467 | 6 3468 | packet 3469 | 1 3470 | 694 3471 | 2 3472 | 19 3473 | paddle, boat paddle 3474 | 1 3475 | 695 3476 | 2 3477 | 25 3478 | paddlewheel, paddle wheel 3479 | 1 3480 | 696 3481 | 2 3482 | 7 3483 | padlock 3484 | 1 3485 | 697 3486 | 2 3487 | 10 3488 | paintbrush 3489 | 1 3490 | 698 3491 | 2 3492 | 29 3493 | pajama, pyjama, pj's, jammies 3494 | 1 3495 | 699 3496 | 2 3497 | 6 3498 | palace 3499 | 1 3500 | 700 3501 | 2 3502 | 29 3503 | panpipe, pandean pipe, syrinx 3504 | 1 3505 | 701 3506 | 2 3507 | 11 3508 | paper towel 3509 | 1 3510 | 702 3511 | 2 3512 | 16 3513 | parachute, chute 3514 | 1 3515 | 703 3516 | 2 3517 | 19 3518 | parallel bars, bars 3519 | 1 3520 | 704 3521 | 2 3522 | 10 3523 | park bench 3524 | 1 3525 | 705 3526 | 2 3527 | 13 3528 | parking meter 3529 | 1 3530 | 706 3531 | 2 3532 | 30 3533 | passenger car, coach, carriage 3534 | 1 3535 | 707 3536 | 2 3537 | 14 3538 | patio, terrace 3539 | 1 3540 | 708 3541 | 2 3542 | 22 3543 | pay-phone, pay-station 3544 | 1 3545 | 709 3546 | 2 3547 | 27 3548 | pedestal, plinth, footstall 3549 | 1 3550 | 710 3551 | 2 3552 | 23 3553 | pencil box, pencil case 3554 | 1 3555 | 711 3556 | 2 3557 | 16 3558 | pencil sharpener 3559 | 1 3560 | 712 3561 | 2 3562 | 16 3563 | perfume, essence 3564 | 1 3565 | 713 3566 | 2 3567 | 10 3568 | Petri dish 3569 | 1 3570 | 714 3571 | 2 3572 | 11 3573 | photocopier 3574 | 1 3575 | 715 3576 | 2 3577 | 24 3578 | pick, plectrum, plectron 3579 | 1 3580 | 716 3581 | 2 3582 | 11 3583 | pickelhaube 3584 | 1 3585 | 717 3586 | 2 3587 | 20 3588 | picket fence, paling 3589 | 1 3590 | 718 3591 | 2 3592 | 20 3593 | pickup, pickup truck 3594 | 1 3595 | 719 3596 | 2 3597 | 4 3598 | pier 3599 | 1 3600 | 720 3601 | 2 3602 | 22 3603 | piggy bank, penny bank 3604 | 1 3605 | 721 3606 | 2 3607 | 11 3608 | pill bottle 3609 | 1 3610 | 722 3611 | 2 3612 | 6 3613 | pillow 3614 | 1 3615 | 723 3616 | 2 3617 | 14 3618 | ping-pong ball 3619 | 1 3620 | 724 3621 | 2 3622 | 8 3623 | pinwheel 3624 | 1 3625 | 725 3626 | 2 3627 | 19 3628 | pirate, pirate ship 3629 | 1 3630 | 726 3631 | 2 3632 | 13 3633 | pitcher, ewer 3634 | 1 3635 | 727 3636 | 2 3637 | 43 3638 | plane, carpenter's plane, woodworking plane 3639 | 1 3640 | 728 3641 | 2 3642 | 11 3643 | planetarium 3644 | 1 3645 | 729 3646 | 2 3647 | 11 3648 | plastic bag 3649 | 1 3650 | 730 3651 | 2 3652 | 10 3653 | plate rack 3654 | 1 3655 | 731 3656 | 2 3657 | 12 3658 | plow, plough 3659 | 1 3660 | 732 3661 | 2 3662 | 25 3663 | plunger, plumber's helper 3664 | 1 3665 | 733 3666 | 2 3667 | 37 3668 | Polaroid camera, Polaroid Land camera 3669 | 1 3670 | 734 3671 | 2 3672 | 4 3673 | pole 3674 | 1 3675 | 735 3676 | 2 3677 | 71 3678 | police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria 3679 | 1 3680 | 736 3681 | 2 3682 | 6 3683 | poncho 3684 | 1 3685 | 737 3686 | 2 3687 | 41 3688 | pool table, billiard table, snooker table 3689 | 1 3690 | 738 3691 | 2 3692 | 23 3693 | pop bottle, soda bottle 3694 | 1 3695 | 739 3696 | 2 3697 | 14 3698 | pot, flowerpot 3699 | 1 3700 | 740 3701 | 2 3702 | 14 3703 | potter's wheel 3704 | 1 3705 | 741 3706 | 2 3707 | 11 3708 | power drill 3709 | 1 3710 | 742 3711 | 2 3712 | 22 3713 | prayer rug, prayer mat 3714 | 1 3715 | 743 3716 | 2 3717 | 7 3718 | printer 3719 | 1 3720 | 744 3721 | 2 3722 | 20 3723 | prison, prison house 3724 | 1 3725 | 745 3726 | 2 3727 | 19 3728 | projectile, missile 3729 | 1 3730 | 746 3731 | 2 3732 | 9 3733 | projector 3734 | 1 3735 | 747 3736 | 2 3737 | 17 3738 | puck, hockey puck 3739 | 1 3740 | 748 3741 | 2 3742 | 49 3743 | punching bag, punch bag, punching ball, punchball 3744 | 1 3745 | 749 3746 | 2 3747 | 5 3748 | purse 3749 | 1 3750 | 750 3751 | 2 3752 | 16 3753 | quill, quill pen 3754 | 1 3755 | 751 3756 | 2 3757 | 31 3758 | quilt, comforter, comfort, puff 3759 | 1 3760 | 752 3761 | 2 3762 | 27 3763 | racer, race car, racing car 3764 | 1 3765 | 753 3766 | 2 3767 | 15 3768 | racket, racquet 3769 | 1 3770 | 754 3771 | 2 3772 | 8 3773 | radiator 3774 | 1 3775 | 755 3776 | 2 3777 | 15 3778 | radio, wireless 3779 | 1 3780 | 756 3781 | 2 3782 | 32 3783 | radio telescope, radio reflector 3784 | 1 3785 | 757 3786 | 2 3787 | 11 3788 | rain barrel 3789 | 1 3790 | 758 3791 | 2 3792 | 30 3793 | recreational vehicle, RV, R.V. 3794 | 1 3795 | 759 3796 | 2 3797 | 4 3798 | reel 3799 | 1 3800 | 760 3801 | 2 3802 | 13 3803 | reflex camera 3804 | 1 3805 | 761 3806 | 2 3807 | 20 3808 | refrigerator, icebox 3809 | 1 3810 | 762 3811 | 2 3812 | 22 3813 | remote control, remote 3814 | 1 3815 | 763 3816 | 2 3817 | 46 3818 | restaurant, eating house, eating place, eatery 3819 | 1 3820 | 764 3821 | 2 3822 | 30 3823 | revolver, six-gun, six-shooter 3824 | 1 3825 | 765 3826 | 2 3827 | 5 3828 | rifle 3829 | 1 3830 | 766 3831 | 2 3832 | 21 3833 | rocking chair, rocker 3834 | 1 3835 | 767 3836 | 2 3837 | 10 3838 | rotisserie 3839 | 1 3840 | 768 3841 | 2 3842 | 36 3843 | rubber eraser, rubber, pencil eraser 3844 | 1 3845 | 769 3846 | 2 3847 | 10 3848 | rugby ball 3849 | 1 3850 | 770 3851 | 2 3852 | 11 3853 | rule, ruler 3854 | 1 3855 | 771 3856 | 2 3857 | 12 3858 | running shoe 3859 | 1 3860 | 772 3861 | 2 3862 | 4 3863 | safe 3864 | 1 3865 | 773 3866 | 2 3867 | 10 3868 | safety pin 3869 | 1 3870 | 774 3871 | 2 3872 | 23 3873 | saltshaker, salt shaker 3874 | 1 3875 | 775 3876 | 2 3877 | 6 3878 | sandal 3879 | 1 3880 | 776 3881 | 2 3882 | 6 3883 | sarong 3884 | 1 3885 | 777 3886 | 2 3887 | 14 3888 | sax, saxophone 3889 | 1 3890 | 778 3891 | 2 3892 | 8 3893 | scabbard 3894 | 1 3895 | 779 3896 | 2 3897 | 23 3898 | scale, weighing machine 3899 | 1 3900 | 780 3901 | 2 3902 | 10 3903 | school bus 3904 | 1 3905 | 781 3906 | 2 3907 | 8 3908 | schooner 3909 | 1 3910 | 782 3911 | 2 3912 | 10 3913 | scoreboard 3914 | 1 3915 | 783 3916 | 2 3917 | 18 3918 | screen, CRT screen 3919 | 1 3920 | 784 3921 | 2 3922 | 5 3923 | screw 3924 | 1 3925 | 785 3926 | 2 3927 | 11 3928 | screwdriver 3929 | 1 3930 | 786 3931 | 2 3932 | 19 3933 | seat belt, seatbelt 3934 | 1 3935 | 787 3936 | 2 3937 | 14 3938 | sewing machine 3939 | 1 3940 | 788 3941 | 2 3942 | 15 3943 | shield, buckler 3944 | 1 3945 | 789 3946 | 2 3947 | 32 3948 | shoe shop, shoe-shop, shoe store 3949 | 1 3950 | 790 3951 | 2 3952 | 5 3953 | shoji 3954 | 1 3955 | 791 3956 | 2 3957 | 15 3958 | shopping basket 3959 | 1 3960 | 792 3961 | 2 3962 | 13 3963 | shopping cart 3964 | 1 3965 | 793 3966 | 2 3967 | 6 3968 | shovel 3969 | 1 3970 | 794 3971 | 2 3972 | 10 3973 | shower cap 3974 | 1 3975 | 795 3976 | 2 3977 | 14 3978 | shower curtain 3979 | 1 3980 | 796 3981 | 2 3982 | 3 3983 | ski 3984 | 1 3985 | 797 3986 | 2 3987 | 8 3988 | ski mask 3989 | 1 3990 | 798 3991 | 2 3992 | 12 3993 | sleeping bag 3994 | 1 3995 | 799 3996 | 2 3997 | 21 3998 | slide rule, slipstick 3999 | 1 4000 | 800 4001 | 2 4002 | 12 4003 | sliding door 4004 | 1 4005 | 801 4006 | 2 4007 | 22 4008 | slot, one-armed bandit 4009 | 1 4010 | 802 4011 | 2 4012 | 7 4013 | snorkel 4014 | 1 4015 | 803 4016 | 2 4017 | 10 4018 | snowmobile 4019 | 1 4020 | 804 4021 | 2 4022 | 20 4023 | snowplow, snowplough 4024 | 1 4025 | 805 4026 | 2 4027 | 14 4028 | soap dispenser 4029 | 1 4030 | 806 4031 | 2 4032 | 11 4033 | soccer ball 4034 | 1 4035 | 807 4036 | 2 4037 | 4 4038 | sock 4039 | 1 4040 | 808 4041 | 2 4042 | 42 4043 | solar dish, solar collector, solar furnace 4044 | 1 4045 | 809 4046 | 2 4047 | 8 4048 | sombrero 4049 | 1 4050 | 810 4051 | 2 4052 | 9 4053 | soup bowl 4054 | 1 4055 | 811 4056 | 2 4057 | 9 4058 | space bar 4059 | 1 4060 | 812 4061 | 2 4062 | 12 4063 | space heater 4064 | 1 4065 | 813 4066 | 2 4067 | 13 4068 | space shuttle 4069 | 1 4070 | 814 4071 | 2 4072 | 7 4073 | spatula 4074 | 1 4075 | 815 4076 | 2 4077 | 9 4078 | speedboat 4079 | 1 4080 | 816 4081 | 2 4082 | 24 4083 | spider web, spider's web 4084 | 1 4085 | 817 4086 | 2 4087 | 7 4088 | spindle 4089 | 1 4090 | 818 4091 | 2 4092 | 21 4093 | sports car, sport car 4094 | 1 4095 | 819 4096 | 2 4097 | 15 4098 | spotlight, spot 4099 | 1 4100 | 820 4101 | 2 4102 | 5 4103 | stage 4104 | 1 4105 | 821 4106 | 2 4107 | 16 4108 | steam locomotive 4109 | 1 4110 | 822 4111 | 2 4112 | 17 4113 | steel arch bridge 4114 | 1 4115 | 823 4116 | 2 4117 | 10 4118 | steel drum 4119 | 1 4120 | 824 4121 | 2 4122 | 11 4123 | stethoscope 4124 | 1 4125 | 825 4126 | 2 4127 | 5 4128 | stole 4129 | 1 4130 | 826 4131 | 2 4132 | 10 4133 | stone wall 4134 | 1 4135 | 827 4136 | 2 4137 | 21 4138 | stopwatch, stop watch 4139 | 1 4140 | 828 4141 | 2 4142 | 5 4143 | stove 4144 | 1 4145 | 829 4146 | 2 4147 | 8 4148 | strainer 4149 | 1 4150 | 830 4151 | 2 4152 | 46 4153 | streetcar, tram, tramcar, trolley, trolley car 4154 | 1 4155 | 831 4156 | 2 4157 | 9 4158 | stretcher 4159 | 1 4160 | 832 4161 | 2 4162 | 21 4163 | studio couch, day bed 4164 | 1 4165 | 833 4166 | 2 4167 | 11 4168 | stupa, tope 4169 | 1 4170 | 834 4171 | 2 4172 | 31 4173 | submarine, pigboat, sub, U-boat 4174 | 1 4175 | 835 4176 | 2 4177 | 21 4178 | suit, suit of clothes 4179 | 1 4180 | 836 4181 | 2 4182 | 7 4183 | sundial 4184 | 1 4185 | 837 4186 | 2 4187 | 8 4188 | sunglass 4189 | 1 4190 | 838 4191 | 2 4192 | 32 4193 | sunglasses, dark glasses, shades 4194 | 1 4195 | 839 4196 | 2 4197 | 32 4198 | sunscreen, sunblock, sun blocker 4199 | 1 4200 | 840 4201 | 2 4202 | 17 4203 | suspension bridge 4204 | 1 4205 | 841 4206 | 2 4207 | 15 4208 | swab, swob, mop 4209 | 1 4210 | 842 4211 | 2 4212 | 10 4213 | sweatshirt 4214 | 1 4215 | 843 4216 | 2 4217 | 31 4218 | swimming trunks, bathing trunks 4219 | 1 4220 | 844 4221 | 2 4222 | 5 4223 | swing 4224 | 1 4225 | 845 4226 | 2 4227 | 42 4228 | switch, electric switch, electrical switch 4229 | 1 4230 | 846 4231 | 2 4232 | 7 4233 | syringe 4234 | 1 4235 | 847 4236 | 2 4237 | 10 4238 | table lamp 4239 | 1 4240 | 848 4241 | 2 4242 | 64 4243 | tank, army tank, armored combat vehicle, armoured combat vehicle 4244 | 1 4245 | 849 4246 | 2 4247 | 11 4248 | tape player 4249 | 1 4250 | 850 4251 | 2 4252 | 6 4253 | teapot 4254 | 1 4255 | 851 4256 | 2 4257 | 17 4258 | teddy, teddy bear 4259 | 1 4260 | 852 4261 | 2 4262 | 29 4263 | television, television system 4264 | 1 4265 | 853 4266 | 2 4267 | 11 4268 | tennis ball 4269 | 1 4270 | 854 4271 | 2 4272 | 21 4273 | thatch, thatched roof 4274 | 1 4275 | 855 4276 | 2 4277 | 32 4278 | theater curtain, theatre curtain 4279 | 1 4280 | 856 4281 | 2 4282 | 7 4283 | thimble 4284 | 1 4285 | 857 4286 | 2 4287 | 37 4288 | thresher, thrasher, threshing machine 4289 | 1 4290 | 858 4291 | 2 4292 | 6 4293 | throne 4294 | 1 4295 | 859 4296 | 2 4297 | 9 4298 | tile roof 4299 | 1 4300 | 860 4301 | 2 4302 | 7 4303 | toaster 4304 | 1 4305 | 861 4306 | 2 4307 | 43 4308 | tobacco shop, tobacconist shop, tobacconist 4309 | 1 4310 | 862 4311 | 2 4312 | 11 4313 | toilet seat 4314 | 1 4315 | 863 4316 | 2 4317 | 5 4318 | torch 4319 | 1 4320 | 864 4321 | 2 4322 | 10 4323 | totem pole 4324 | 1 4325 | 865 4326 | 2 4327 | 27 4328 | tow truck, tow car, wrecker 4329 | 1 4330 | 866 4331 | 2 4332 | 7 4333 | toyshop 4334 | 1 4335 | 867 4336 | 2 4337 | 7 4338 | tractor 4339 | 1 4340 | 868 4341 | 2 4342 | 74 4343 | trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi 4344 | 1 4345 | 869 4346 | 2 4347 | 4 4348 | tray 4349 | 1 4350 | 870 4351 | 2 4352 | 11 4353 | trench coat 4354 | 1 4355 | 871 4356 | 2 4357 | 27 4358 | tricycle, trike, velocipede 4359 | 1 4360 | 872 4361 | 2 4362 | 8 4363 | trimaran 4364 | 1 4365 | 873 4366 | 2 4367 | 6 4368 | tripod 4369 | 1 4370 | 874 4371 | 2 4372 | 14 4373 | triumphal arch 4374 | 1 4375 | 875 4376 | 2 4377 | 44 4378 | trolleybus, trolley coach, trackless trolley 4379 | 1 4380 | 876 4381 | 2 4382 | 8 4383 | trombone 4384 | 1 4385 | 877 4386 | 2 4387 | 8 4388 | tub, vat 4389 | 1 4390 | 878 4391 | 2 4392 | 9 4393 | turnstile 4394 | 1 4395 | 879 4396 | 2 4397 | 19 4398 | typewriter keyboard 4399 | 1 4400 | 880 4401 | 2 4402 | 8 4403 | umbrella 4404 | 1 4405 | 881 4406 | 2 4407 | 19 4408 | unicycle, monocycle 4409 | 1 4410 | 882 4411 | 2 4412 | 22 4413 | upright, upright piano 4414 | 1 4415 | 883 4416 | 2 4417 | 22 4418 | vacuum, vacuum cleaner 4419 | 1 4420 | 884 4421 | 2 4422 | 4 4423 | vase 4424 | 1 4425 | 885 4426 | 2 4427 | 5 4428 | vault 4429 | 1 4430 | 886 4431 | 2 4432 | 6 4433 | velvet 4434 | 1 4435 | 887 4436 | 2 4437 | 15 4438 | vending machine 4439 | 1 4440 | 888 4441 | 2 4442 | 8 4443 | vestment 4444 | 1 4445 | 889 4446 | 2 4447 | 7 4448 | viaduct 4449 | 1 4450 | 890 4451 | 2 4452 | 14 4453 | violin, fiddle 4454 | 1 4455 | 891 4456 | 2 4457 | 10 4458 | volleyball 4459 | 1 4460 | 892 4461 | 2 4462 | 11 4463 | waffle iron 4464 | 1 4465 | 893 4466 | 2 4467 | 10 4468 | wall clock 4469 | 1 4470 | 894 4471 | 2 4472 | 38 4473 | wallet, billfold, notecase, pocketbook 4474 | 1 4475 | 895 4476 | 2 4477 | 23 4478 | wardrobe, closet, press 4479 | 1 4480 | 896 4481 | 2 4482 | 24 4483 | warplane, military plane 4484 | 1 4485 | 897 4486 | 2 4487 | 55 4488 | washbasin, handbasin, washbowl, lavabo, wash-hand basin 4489 | 1 4490 | 898 4491 | 2 4492 | 41 4493 | washer, automatic washer, washing machine 4494 | 1 4495 | 899 4496 | 2 4497 | 12 4498 | water bottle 4499 | 1 4500 | 900 4501 | 2 4502 | 9 4503 | water jug 4504 | 1 4505 | 901 4506 | 2 4507 | 11 4508 | water tower 4509 | 1 4510 | 902 4511 | 2 4512 | 11 4513 | whiskey jug 4514 | 1 4515 | 903 4516 | 2 4517 | 7 4518 | whistle 4519 | 1 4520 | 904 4521 | 2 4522 | 3 4523 | wig 4524 | 1 4525 | 905 4526 | 2 4527 | 13 4528 | window screen 4529 | 1 4530 | 906 4531 | 2 4532 | 12 4533 | window shade 4534 | 1 4535 | 907 4536 | 2 4537 | 11 4538 | Windsor tie 4539 | 1 4540 | 908 4541 | 2 4542 | 11 4543 | wine bottle 4544 | 1 4545 | 909 4546 | 2 4547 | 4 4548 | wing 4549 | 1 4550 | 910 4551 | 2 4552 | 3 4553 | wok 4554 | 1 4555 | 911 4556 | 2 4557 | 12 4558 | wooden spoon 4559 | 1 4560 | 912 4561 | 2 4562 | 21 4563 | wool, woolen, woollen 4564 | 1 4565 | 913 4566 | 2 4567 | 57 4568 | worm fence, snake fence, snake-rail fence, Virginia fence 4569 | 1 4570 | 914 4571 | 2 4572 | 5 4573 | wreck 4574 | 1 4575 | 915 4576 | 2 4577 | 4 4578 | yawl 4579 | 1 4580 | 916 4581 | 2 4582 | 4 4583 | yurt 4584 | 1 4585 | 917 4586 | 2 4587 | 38 4588 | web site, website, internet site, site 4589 | 1 4590 | 918 4591 | 2 4592 | 10 4593 | comic book 4594 | 1 4595 | 919 4596 | 2 4597 | 27 4598 | crossword puzzle, crossword 4599 | 1 4600 | 920 4601 | 2 4602 | 11 4603 | street sign 4604 | 1 4605 | 921 4606 | 2 4607 | 40 4608 | traffic light, traffic signal, stoplight 4609 | 1 4610 | 922 4611 | 2 4612 | 50 4613 | book jacket, dust cover, dust jacket, dust wrapper 4614 | 1 4615 | 923 4616 | 2 4617 | 4 4618 | menu 4619 | 1 4620 | 924 4621 | 2 4622 | 5 4623 | plate 4624 | 1 4625 | 925 4626 | 2 4627 | 9 4628 | guacamole 4629 | 1 4630 | 926 4631 | 2 4632 | 8 4633 | consomme 4634 | 1 4635 | 927 4636 | 2 4637 | 15 4638 | hot pot, hotpot 4639 | 1 4640 | 928 4641 | 2 4642 | 6 4643 | trifle 4644 | 1 4645 | 929 4646 | 2 4647 | 19 4648 | ice cream, icecream 4649 | 1 4650 | 930 4651 | 2 4652 | 36 4653 | ice lolly, lolly, lollipop, popsicle 4654 | 1 4655 | 931 4656 | 2 4657 | 11 4658 | French loaf 4659 | 1 4660 | 932 4661 | 2 4662 | 13 4663 | bagel, beigel 4664 | 1 4665 | 933 4666 | 2 4667 | 7 4668 | pretzel 4669 | 1 4670 | 934 4671 | 2 4672 | 12 4673 | cheeseburger 4674 | 1 4675 | 935 4676 | 2 4677 | 24 4678 | hotdog, hot dog, red hot 4679 | 1 4680 | 936 4681 | 2 4682 | 13 4683 | mashed potato 4684 | 1 4685 | 937 4686 | 2 4687 | 12 4688 | head cabbage 4689 | 1 4690 | 938 4691 | 2 4692 | 8 4693 | broccoli 4694 | 1 4695 | 939 4696 | 2 4697 | 11 4698 | cauliflower 4699 | 1 4700 | 940 4701 | 2 4702 | 19 4703 | zucchini, courgette 4704 | 1 4705 | 941 4706 | 2 4707 | 16 4708 | spaghetti squash 4709 | 1 4710 | 942 4711 | 2 4712 | 12 4713 | acorn squash 4714 | 1 4715 | 943 4716 | 2 4717 | 16 4718 | butternut squash 4719 | 1 4720 | 944 4721 | 2 4722 | 14 4723 | cucumber, cuke 4724 | 1 4725 | 945 4726 | 2 4727 | 26 4728 | artichoke, globe artichoke 4729 | 1 4730 | 946 4731 | 2 4732 | 11 4733 | bell pepper 4734 | 1 4735 | 947 4736 | 2 4737 | 7 4738 | cardoon 4739 | 1 4740 | 948 4741 | 2 4742 | 8 4743 | mushroom 4744 | 1 4745 | 949 4746 | 2 4747 | 12 4748 | Granny Smith 4749 | 1 4750 | 950 4751 | 2 4752 | 10 4753 | strawberry 4754 | 1 4755 | 951 4756 | 2 4757 | 6 4758 | orange 4759 | 1 4760 | 952 4761 | 2 4762 | 5 4763 | lemon 4764 | 1 4765 | 953 4766 | 2 4767 | 3 4768 | fig 4769 | 1 4770 | 954 4771 | 2 4772 | 17 4773 | pineapple, ananas 4774 | 1 4775 | 955 4776 | 2 4777 | 6 4778 | banana 4779 | 1 4780 | 956 4781 | 2 4782 | 20 4783 | jackfruit, jak, jack 4784 | 1 4785 | 957 4786 | 2 4787 | 13 4788 | custard apple 4789 | 1 4790 | 958 4791 | 2 4792 | 11 4793 | pomegranate 4794 | 1 4795 | 959 4796 | 2 4797 | 3 4798 | hay 4799 | 1 4800 | 960 4801 | 2 4802 | 9 4803 | carbonara 4804 | 1 4805 | 961 4806 | 2 4807 | 32 4808 | chocolate sauce, chocolate syrup 4809 | 1 4810 | 962 4811 | 2 4812 | 5 4813 | dough 4814 | 1 4815 | 963 4816 | 2 4817 | 19 4818 | meat loaf, meatloaf 4819 | 1 4820 | 964 4821 | 2 4822 | 16 4823 | pizza, pizza pie 4824 | 1 4825 | 965 4826 | 2 4827 | 6 4828 | potpie 4829 | 1 4830 | 966 4831 | 2 4832 | 7 4833 | burrito 4834 | 1 4835 | 967 4836 | 2 4837 | 8 4838 | red wine 4839 | 1 4840 | 968 4841 | 2 4842 | 8 4843 | espresso 4844 | 1 4845 | 969 4846 | 2 4847 | 3 4848 | cup 4849 | 1 4850 | 970 4851 | 2 4852 | 6 4853 | eggnog 4854 | 1 4855 | 971 4856 | 2 4857 | 3 4858 | alp 4859 | 1 4860 | 972 4861 | 2 4862 | 6 4863 | bubble 4864 | 1 4865 | 973 4866 | 2 4867 | 21 4868 | cliff, drop, drop-off 4869 | 1 4870 | 974 4871 | 2 4872 | 10 4873 | coral reef 4874 | 1 4875 | 975 4876 | 2 4877 | 6 4878 | geyser 4879 | 1 4880 | 976 4881 | 2 4882 | 19 4883 | lakeside, lakeshore 4884 | 1 4885 | 977 4886 | 2 4887 | 36 4888 | promontory, headland, head, foreland 4889 | 1 4890 | 978 4891 | 2 4892 | 17 4893 | sandbar, sand bar 4894 | 1 4895 | 979 4896 | 2 4897 | 36 4898 | seashore, coast, seacoast, sea-coast 4899 | 1 4900 | 980 4901 | 2 4902 | 12 4903 | valley, vale 4904 | 1 4905 | 981 4906 | 2 4907 | 7 4908 | volcano 4909 | 1 4910 | 982 4911 | 2 4912 | 27 4913 | ballplayer, baseball player 4914 | 1 4915 | 983 4916 | 2 4917 | 17 4918 | groom, bridegroom 4919 | 1 4920 | 984 4921 | 2 4922 | 11 4923 | scuba diver 4924 | 1 4925 | 985 4926 | 2 4927 | 8 4928 | rapeseed 4929 | 1 4930 | 986 4931 | 2 4932 | 5 4933 | daisy 4934 | 1 4935 | 987 4936 | 2 4937 | 90 4938 | yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum 4939 | 1 4940 | 988 4941 | 2 4942 | 4 4943 | corn 4944 | 1 4945 | 989 4946 | 2 4947 | 5 4948 | acorn 4949 | 1 4950 | 990 4951 | 2 4952 | 22 4953 | hip, rose hip, rosehip 4954 | 1 4955 | 991 4956 | 2 4957 | 31 4958 | buckeye, horse chestnut, conker 4959 | 1 4960 | 992 4961 | 2 4962 | 12 4963 | coral fungus 4964 | 1 4965 | 993 4966 | 2 4967 | 6 4968 | agaric 4969 | 1 4970 | 994 4971 | 2 4972 | 9 4973 | gyromitra 4974 | 1 4975 | 995 4976 | 2 4977 | 25 4978 | stinkhorn, carrion fungus 4979 | 1 4980 | 996 4981 | 2 4982 | 9 4983 | earthstar 4984 | 1 4985 | 997 4986 | 2 4987 | 73 4988 | hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa 4989 | 1 4990 | 998 4991 | 2 4992 | 6 4993 | bolete 4994 | 1 4995 | 999 4996 | 2 4997 | 21 4998 | ear, spike, capitulum 4999 | 1 5000 | 1000 5001 | 2 5002 | 44 5003 | toilet tissue, toilet paper, bathroom tissue 5004 | --------------------------------------------------------------------------------