├── .idea ├── .gitignore ├── Image_processing.iml ├── inspectionProfiles │ └── profiles_settings.xml ├── misc.xml ├── modules.xml ├── other.xml └── vcs.xml ├── Detailed-Paper.pdf ├── LICENSE ├── README.md ├── first_image ├── first_image.py ├── out_data │ ├── canny_edge_test_image1.jpg │ ├── counter_sticks_image1.jpg │ ├── custom_binary_first1.jpg │ ├── edge_processing1.jpg │ ├── fourier_edge_test_image1.jpg │ ├── global_binary_first1.jpg │ ├── gradient_image1.jpg │ ├── gray_cutting_image1.jpg │ ├── gray_edge_test.jpg │ ├── local_binary_first1.jpg │ ├── raw_cutting_image1.jpg │ └── raw_draw_image1.jpg └── raw_data │ ├── 1.JPG │ ├── custom_binary_first1.jpg │ ├── edge_processing1.jpg │ ├── gradient_image1.jpg │ ├── gray_cutting_image1.jpg │ └── icon4.jpg ├── imgs ├── 1.png ├── 10.png ├── 11.png ├── 12.png ├── 13.jpg ├── 13.png ├── 14.png ├── 15.png ├── 16.png ├── 17.png ├── 18.png ├── 2.JPG ├── 3.png ├── 4.png ├── 5.png ├── 6.png ├── 7.jpg ├── 8.png └── 9.png ├── other_image ├── counter_sticks.py ├── edge_cutting.py ├── first_image.py ├── last_test.py ├── main.py ├── other_image.py ├── out_data │ ├── canny_edge_test_image1.jpg │ ├── counter_sticks_image1.jpg │ ├── custom_binary_first1.jpg │ ├── edge_processing1.jpg │ ├── fourier_edge_test_image1.jpg │ ├── global_binary_first1.jpg │ ├── gradient_image1.jpg │ ├── gray_edge_test.jpg │ ├── gray_sharpen_1_Image1.jpg │ ├── gray_sharpen_2_Image1.jpg │ ├── gray_sharpen_3_Image1.jpg │ ├── local_binary_first1.jpg │ ├── sharpen_1_Image1.jpg │ ├── sharpen_2_Image1.jpg │ └── sharpen_3_Image1.jpg ├── raw_data │ ├── 1.jpg │ ├── 2.jpg │ ├── 3.jpg │ ├── 4.jpg │ ├── 5.jpg │ ├── 6.jpg │ ├── 7.jpg │ ├── icon10.png │ ├── icon11.png │ ├── icon_timg.jpg │ ├── icon_timgber4.png │ ├── mucai-003 (1).jpg │ ├── processing_.png │ ├── timber4.jpg │ └── timg.jpg ├── test2.py ├── test4.py └── 分水岭.py ├── problems.docx └── requirements.txt /.idea/.gitignore: -------------------------------------------------------------------------------- 1 | # Default ignored files 2 | /workspace.xml -------------------------------------------------------------------------------- /.idea/Image_processing.iml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 12 | -------------------------------------------------------------------------------- /.idea/inspectionProfiles/profiles_settings.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 6 | -------------------------------------------------------------------------------- /.idea/misc.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 6 | 7 | -------------------------------------------------------------------------------- /.idea/modules.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | -------------------------------------------------------------------------------- /.idea/other.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 7 | -------------------------------------------------------------------------------- /.idea/vcs.xml: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | 5 | 6 | -------------------------------------------------------------------------------- /Detailed-Paper.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/Detailed-Paper.pdf -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # 基于物体轮廓检测和特征提取的木材图像计数模型 2 | 3 | ​ **模型解决问题：使用计算机算法来处理木材照片，从照片中直接计算得知木 材的数量。** 4 | 5 | #### 一.运行环境配置 6 | 7 | 1. python==3.6 8 | 2. Opencv== 3.4.2.16 (这里注意SIFT算法已经申请专利，高版本的该算法已经移除) 9 | 3. matplotlib==3.1.1 10 | 4. ..... 11 | 12 | 具体详细库信息配置见requirements.txt. 13 | 14 | 可以使用下面命令直接配置相关环境。 15 | 16 | ```python 17 | pip install -r requirements.txt 18 | ``` 19 | 20 | 如果执行上面pip指令失败，可以考虑正常安装opencv类库，然后执行以下代码： 21 | 22 | ```python 23 | pip uninstall opencv-python 24 | #推荐使用豆瓣python源 25 | pip install opencv-python==3.4.2.16 -i "https://pypi.doubanio.com/simple/" 26 | pip install opencv-contrib-python==3.4.2.16 -i "https://pypi.doubanio.com/simple/" 27 | ``` 28 | 29 | 对于如果执行程序出现 30 | 31 | AttributeError: module 'cv2.cv2' has no attribute 'xfeatures2d'之类因为算法是否开源的问题，可以从新执行以下代码 32 | 33 | ```python 34 | pip uninstall opencv-python 35 | #推荐使用豆瓣python源 36 | pip install opencv-python==3.4.2.16 -i "https://pypi.doubanio.com/simple/" 37 | pip install opencv-contrib-python==3.4.2.16 -i "https://pypi.doubanio.com/simple/" 38 | ``` 39 | 40 | #### 二.程序整体代码说明 41 | 42 | 本程序分为两部分： 43 | 44 | 1. **模型一**基于环境对计数影响不大其检测目标较为清晰辨别的图片进行木材计数模型如下图： 45 | 46 |
Image text 47 | 48 | 具体代码见other_image文件中的代码。这个主要的代码为main.py文件，其他的为辅助文件，用于探索和评价相关的方法是否适合。 49 | 50 | 2. **模型二**基于环境（光照）对影响计数较大且辨别较难的图片进行木材计数模型如下图： 51 | 52 | 53 | 54 |
Image text 55 | 56 | 具体代码见first_iamge文件中的first_image.py,第二个模型实现了有关的自动化脚本的功能。 57 | 58 | #### 三. 模型一 59 | 60 | 处理原图如下： 61 | 62 |
Image text 63 | 64 | 预处理流程图如下： 65 | 66 |
Image text 67 | 68 | 预处理后得到图像如下： 69 | 70 |
Image text 71 | 72 | 对图像进行SIFT算法处理得到结果图如下： 73 | 74 |
Image text 75 | 76 | 使用联通法对木材图片中的木材进行计数效果图如下： 77 | 78 |
Image text 79 | 80 | 具体详细代码可以参考other_image文件夹中的如下文件： 81 | 82 | counter_sticks.py 、edge_cutting.py、last_test.py、main.py、test2.py、test4.py、分水岭.py 83 | 84 | #### 四. 模型二 85 | 86 | 处理原图为： 87 | 88 | Image text 89 | 90 | 预处理流程图如下： 91 | 92 |
Image text 93 | 94 | ​ 95 | 96 | 灰度化图 97 | 98 |
Image text 99 | 100 | 闭运算预处理 101 | 102 |
Image text 103 | 104 | 开运算预处理 105 | 106 |
Image text 107 | 108 | 梯度运算预处理 109 | 110 |
Image text 111 | 112 | 顶帽运算 113 | 114 |
Image text 115 | 116 | 黑帽运算 117 | 118 |
Image text 119 | 120 |
Image text 121 | 122 | 该部分程序的主要思想：使用图像分割，以及图像边缘检测、和图像进行特征点匹配算法。 123 | 124 | 边缘增强图像如下： 125 | 126 |
Image text 127 | 128 | 沙子边缘检测结果 129 | 130 |
Image text 131 | 132 | 去除沙子影响的灰度图 133 | 134 |
Image text 135 | 136 | 进行图像分割后的边缘检测算法结果图： 137 | 138 |
Image text 139 | 140 | 最后通过特征点匹配进行木材计数功能。 141 | 142 |
Image text 143 | 144 | 145 | 146 | -------------------------------------------------------------------------------- /first_image/first_image.py: -------------------------------------------------------------------------------- 1 | # _*_ coding: utf-8 _*_ 2 | __author__ = 'LelandYan' 3 | __date__ = '2019/5/16 19:32' 4 | import numpy as np 5 | import cv2 6 | import matplotlib.pyplot as plt 7 | import copy 8 | from pylab import mpl 9 | import skimage 10 | # 防止中文乱码 11 | mpl.rcParams['font.sans-serif'] = ['SimHei'] 12 | 13 | 14 | class processing_image: 15 | def __init__(self, filename="./raw_data/1.jpg", output="./out_data"): 16 | self.filename = filename 17 | self.output = output 18 | 19 | def op_gray_to_four_type(self, kernel=(9, 9), erode_iter=5, dilate_iter=5): 20 | 21 | img = cv2.imread(self.filename) 22 | # gray 23 | img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) 24 | # erode dilate 25 | closed = cv2.erode(img, None, iterations=erode_iter) 26 | img = cv2.dilate(closed, None, iterations=dilate_iter) 27 | 28 | kernel = np.ones(kernel, np.uint8) 29 | # open operation 30 | img_open = cv2.morphologyEx(img, op=cv2.MORPH_OPEN, kernel=kernel) 31 | # close operation 32 | img_close = cv2.morphologyEx(img, op=cv2.MORPH_CLOSE, kernel=kernel) 33 | # gradient operation 34 | img_grad = cv2.morphologyEx(img, op=cv2.MORPH_GRADIENT, kernel=kernel) 35 | # tophat operation 36 | img_tophat = cv2.morphologyEx(img, op=cv2.MORPH_TOPHAT, kernel=kernel) 37 | # blackhat operation 38 | img_blackhat = cv2.morphologyEx(img, op=cv2.MORPH_BLACKHAT, kernel=kernel) 39 | # Plot the images 40 | images = [img, img_open, img_close, img_grad, 41 | img_tophat, img_blackhat] 42 | names = ["raw_img", "img_open", "img_close", "img_grad", "img_tophat", "img_blackhat"] 43 | cv2.imwrite(self.output+"/gradient_image1.jpg",img_grad) 44 | fig, axs = plt.subplots(nrows=2, ncols=3, figsize=(15, 15)) 45 | for ind, p in enumerate(images): 46 | ax = axs[ind // 3, ind % 3] 47 | ax.imshow(p, cmap='gray') 48 | ax.set_title(names[ind]) 49 | ax.axis('off') 50 | plt.show() 51 | 52 | def op_first_to_three_type(self, flag=False): 53 | # 全局阈值 54 | def threshold_demo(image): 55 | gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) # 把输入图像灰度化 56 | # 直接阈值化是对输入的单通道矩阵逐像素进行阈值分割。 57 | ret, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_TRIANGLE) 58 | if flag: 59 | cv2.imwrite(self.output + "/global_binary_first1.jpg", binary) 60 | return binary 61 | 62 | # 局部阈值 63 | def local_threshold(image): 64 | gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) # 把输入图像灰度化 65 | # 自适应阈值化能够根据图像不同区域亮度分布，改变阈值 66 | binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 25, 10) 67 | 68 | if flag: 69 | cv2.imwrite(self.output + "/local_binary_first1.jpg", binary) 70 | return binary 71 | 72 | # 用户自己计算阈值 73 | def custom_threshold(image): 74 | gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) # 把输入图像灰度化 75 | h, w = gray.shape[:2] 76 | m = np.reshape(gray, [1, w * h]) 77 | mean = m.sum() / (w * h) 78 | ret, binary = cv2.threshold(gray, mean, 255, cv2.THRESH_BINARY) 79 | if flag: 80 | cv2.imwrite(self.output + "/custom_binary_first1.jpg", binary) 81 | return binary 82 | 83 | if flag: 84 | src = cv2.imread("./out_data/gray_cutting_image1.jpg") 85 | else: 86 | src = cv2.imread(self.filename) 87 | src = cv2.cvtColor(src, cv2.COLOR_BGR2RGB) 88 | global_scr = threshold_demo(src) 89 | local_scr = local_threshold(src) 90 | custom_src = custom_threshold(src) 91 | images = [src, global_scr, local_scr, 92 | custom_src] 93 | names = ["src", "global_scr", "local_scr", "custom_src"] 94 | fig, axs = plt.subplots(nrows=2, ncols=2, figsize=(10, 10)) 95 | for ind, p in enumerate(images): 96 | ax = axs[ind // 2, ind % 2] 97 | ax.imshow(p, cmap='gray') 98 | ax.set_title(names[ind]) 99 | ax.axis('off') 100 | plt.show() 101 | 102 | def op_cutting_image(self): 103 | raw_img = cv2.imread(self.filename) 104 | img = cv2.imread("./out_data/gradient_image1.jpg") 105 | gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) 106 | blurred = cv2.bilateralFilter(gray, 7, sigmaSpace=75, sigmaColor=75) 107 | ret, binary = cv2.threshold(blurred, 127, 255, cv2.THRESH_BINARY) 108 | closed = cv2.dilate(binary, None, iterations=130) 109 | closed = cv2.erode(closed, None, iterations=127) 110 | 111 | _, contours, hierarchy = cv2.findContours(closed, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) 112 | c = sorted(contours, key=cv2.contourArea, reverse=True)[0] 113 | 114 | # compute the rotated bounding box of the largest contour 115 | rect = cv2.minAreaRect(c) 116 | box = np.int0(cv2.boxPoints(rect)) 117 | # draw a bounding box arounded the detected barcode and display the image 118 | draw_img = cv2.drawContours(raw_img.copy(), [box], -1, (0, 0, 255), 3) 119 | 120 | h, w, _ = img.shape 121 | Xs = [i[0] for i in box] 122 | Ys = [i[1] for i in box] 123 | x1 = min(Xs) 124 | x2 = max(Xs) 125 | y1 = min(Ys) 126 | y2 = max(Ys) 127 | hight = y2 - y1 128 | width = x2 - x1 129 | crop_img = img[0:h - hight, x1:x1 + width] 130 | raw_img = raw_img[0:h - hight, x1:x1 + width] 131 | cv2.imwrite(self.output + "/raw_draw_image1.jpg", draw_img) 132 | cv2.imwrite(self.output + "/raw_cutting_image1.jpg", raw_img) 133 | cv2.imwrite(self.output + "/gray_cutting_image1.jpg", crop_img) 134 | 135 | def op_edge_test(self): 136 | def gray_dege_test(): 137 | img = cv2.imread("./out_data/gradient_image1.jpg") 138 | gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) 139 | blurred = cv2.GaussianBlur(gray, (9, 9), 0) 140 | ret, binary = cv2.threshold(blurred, 127, 255, cv2.THRESH_BINARY) 141 | closed = cv2.dilate(binary, None, iterations=110) 142 | closed = cv2.erode(closed, None, iterations=120) 143 | 144 | _, contours, hierarchy = cv2.findContours(closed, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) 145 | 146 | cv2.drawContours(img, contours, -1, (0, 0, 255), 3) 147 | plt.imshow(img) 148 | plt.show() 149 | cv2.imwrite(self.output + "/gray_edge_test.jpg", img) 150 | 151 | def fourier_edge_test(): 152 | img = cv2.imread('./out_data/gradient_image1.jpg', 0) 153 | f = np.fft.fft2(img) 154 | fshift = np.fft.fftshift(f) 155 | 156 | rows, cols = img.shape 157 | crow, ccol = int(rows / 2), int(cols / 2) 158 | for i in range(crow - 30, crow + 30): 159 | for j in range(ccol - 30, ccol + 30): 160 | fshift[i][j] = 0.0 161 | f_ishift = np.fft.ifftshift(fshift) 162 | img_back = np.fft.ifft2(f_ishift) # 进行高通滤波 163 | # 取绝对值 164 | img_back = np.abs(img_back) 165 | plt.subplot(121), plt.imshow(img, cmap='gray') # 因图像格式问题，暂已灰度输出 166 | plt.title('Input Image'), plt.xticks([]), plt.yticks([]) 167 | # 先对灰度图像进行伽马变换，以提升暗部细节 168 | rows, cols = img_back.shape 169 | gamma = copy.deepcopy(img_back) 170 | rows = img.shape[0] 171 | cols = img.shape[1] 172 | for i in range(rows): 173 | for j in range(cols): 174 | gamma[i][j] = 5.0 * pow(gamma[i][j], 0.34) # 0.34这个参数是我手动调出来的，根据不同的图片，可以选择不同的数值 175 | # 对灰度图像进行反转 176 | 177 | for i in range(rows): 178 | for j in range(cols): 179 | gamma[i][j] = 255 - gamma[i][j] 180 | 181 | plt.subplot(122), plt.imshow(gamma, cmap='gray') 182 | plt.title('Result in HPF'), plt.xticks([]), plt.yticks([]) 183 | cv2.imwrite(self.output + "/fourier_edge_test_image1.jpg", gamma) 184 | plt.show() 185 | 186 | def canny_edge_test(): 187 | img = cv2.imread('./out_data/gradient_image1.jpg', 0) 188 | edges = cv2.Canny(img, 100, 200) 189 | 190 | plt.subplot(121), plt.imshow(img, cmap='gray') 191 | plt.title('original'), plt.xticks([]), plt.yticks([]) 192 | plt.subplot(122), plt.imshow(edges, cmap='gray') 193 | plt.title('edge'), plt.xticks([]), plt.yticks([]) 194 | cv2.imwrite(self.output + "/canny_edge_test_image1.jpg", edges) 195 | plt.show() 196 | 197 | gray_dege_test() 198 | fourier_edge_test() 199 | canny_edge_test() 200 | 201 | def op_trans_plot(self): 202 | im_in = cv2.imread("./out_data/custom_binary_first1.jpg", cv2.IMREAD_GRAYSCALE) 203 | th, im_th = cv2.threshold(im_in, 220, 255, cv2.THRESH_BINARY_INV) 204 | 205 | # Copy the thresholded image. 206 | im_floodfill = im_th.copy() 207 | 208 | # Mask used to flood filling. 209 | # Notice the size needs to be 2 pixels than the image. 210 | h, w = im_th.shape[:2] 211 | mask = np.zeros((h + 2, w + 2), np.uint8) 212 | 213 | # Floodfill from point (0, 0) 214 | cv2.floodFill(im_floodfill, mask, (0, 0), 255) 215 | cv2.imwrite(self.output + "/edge_processing1.jpg", im_floodfill) 216 | 217 | def op_counter(self): 218 | ob1 = cv2.imread("./out_data/edge_processing1.jpg", cv2.IMREAD_GRAYSCALE) 219 | # ob1 = cv2.dilate(ob1, None, iterations=2) 220 | ob1 = cv2.bilateralFilter(ob1, 7, sigmaSpace=70, sigmaColor=70) 221 | ob1 = cv2.erode(ob1, None, iterations=2) # 1 # 2 222 | ob1 = cv2.dilate(ob1, None, iterations=2) 223 | ob2 = cv2.imread("./raw_data/icon4.jpg", cv2.IMREAD_GRAYSCALE) 224 | # ob2 = cv2.bilateralFilter(ob2, 7, sigmaSpace=60, sigmaColor=60) 225 | ob2 = cv2.erode(ob2, None, iterations=1) 226 | # ob2 = cv2.dilate(ob2, None, iterations=1) 227 | # orb = cv2.xfeatures2d.SURF_create() 228 | orb = cv2.xfeatures2d.SIFT_create() 229 | keyp1, desp1 = orb.detectAndCompute(ob1, None) 230 | keyp2, desp2 = orb.detectAndCompute(ob2, None) 231 | FLANN_INDEX_KDTREE = 1 232 | index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5) 233 | search_params = dict(checks=50) 234 | flann = cv2.FlannBasedMatcher(index_params, search_params) 235 | matches = flann.knnMatch(desp1, desp2, k=2) 236 | matchesMask = [[0, 0] for i in range(len(matches))] 237 | for i, (m, n) in enumerate(matches): 238 | if m.distance < 0.7 * n.distance: 239 | matchesMask[i] = [1, 0] 240 | # 如果第一个邻近距离比第二个邻近距离的0.7倍小，则保留 241 | draw_params = dict(matchColor=(0, 255, 0), singlePointColor=(255, 0, 0), matchesMask=matchesMask, flags=0) 242 | img3 = cv2.drawMatchesKnn(ob1, keyp1, ob2, keyp2, matches, None, **draw_params) 243 | a = len(keyp1) // len(keyp2) 244 | plt.figure(figsize=(8, 8)) 245 | plt.subplot(211) 246 | plt.imshow(img3) 247 | plt.subplot(212) 248 | plt.text(0.5, 0.6, "the number of sticks:" + str(a), size=30, ha="center", va="center") 249 | plt.axis('off') 250 | plt.show() 251 | cv2.imwrite(self.output+"/counter_sticks_image1.jpg", img3) 252 | 253 | if __name__ == '__main__': 254 | ob = processing_image() 255 | ob.op_gray_to_four_type() 256 | ob.op_first_to_three_type() 257 | # ob.op_cutting_image() 258 | ob.op_edge_test() 259 | ob.op_trans_plot() 260 | ob.op_first_to_three_type(flag=True) 261 | ob.op_counter() 262 | -------------------------------------------------------------------------------- /first_image/out_data/canny_edge_test_image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/out_data/canny_edge_test_image1.jpg -------------------------------------------------------------------------------- /first_image/out_data/counter_sticks_image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/out_data/counter_sticks_image1.jpg -------------------------------------------------------------------------------- /first_image/out_data/custom_binary_first1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/out_data/custom_binary_first1.jpg -------------------------------------------------------------------------------- /first_image/out_data/edge_processing1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/out_data/edge_processing1.jpg -------------------------------------------------------------------------------- /first_image/out_data/fourier_edge_test_image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/out_data/fourier_edge_test_image1.jpg -------------------------------------------------------------------------------- /first_image/out_data/global_binary_first1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/out_data/global_binary_first1.jpg -------------------------------------------------------------------------------- /first_image/out_data/gradient_image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/out_data/gradient_image1.jpg -------------------------------------------------------------------------------- /first_image/out_data/gray_cutting_image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/out_data/gray_cutting_image1.jpg -------------------------------------------------------------------------------- /first_image/out_data/gray_edge_test.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/out_data/gray_edge_test.jpg -------------------------------------------------------------------------------- /first_image/out_data/local_binary_first1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/out_data/local_binary_first1.jpg -------------------------------------------------------------------------------- /first_image/out_data/raw_cutting_image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/out_data/raw_cutting_image1.jpg -------------------------------------------------------------------------------- /first_image/out_data/raw_draw_image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/out_data/raw_draw_image1.jpg -------------------------------------------------------------------------------- /first_image/raw_data/1.JPG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/raw_data/1.JPG -------------------------------------------------------------------------------- /first_image/raw_data/custom_binary_first1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/raw_data/custom_binary_first1.jpg -------------------------------------------------------------------------------- /first_image/raw_data/edge_processing1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/raw_data/edge_processing1.jpg -------------------------------------------------------------------------------- /first_image/raw_data/gradient_image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/raw_data/gradient_image1.jpg -------------------------------------------------------------------------------- /first_image/raw_data/gray_cutting_image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/raw_data/gray_cutting_image1.jpg -------------------------------------------------------------------------------- /first_image/raw_data/icon4.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/first_image/raw_data/icon4.jpg -------------------------------------------------------------------------------- /imgs/1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/1.png -------------------------------------------------------------------------------- /imgs/10.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/10.png -------------------------------------------------------------------------------- /imgs/11.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/11.png -------------------------------------------------------------------------------- /imgs/12.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/12.png -------------------------------------------------------------------------------- /imgs/13.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/13.jpg -------------------------------------------------------------------------------- /imgs/13.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/13.png -------------------------------------------------------------------------------- /imgs/14.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/14.png -------------------------------------------------------------------------------- /imgs/15.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/15.png -------------------------------------------------------------------------------- /imgs/16.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/16.png -------------------------------------------------------------------------------- /imgs/17.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/17.png -------------------------------------------------------------------------------- /imgs/18.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/18.png -------------------------------------------------------------------------------- /imgs/2.JPG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/2.JPG -------------------------------------------------------------------------------- /imgs/3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/3.png -------------------------------------------------------------------------------- /imgs/4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/4.png -------------------------------------------------------------------------------- /imgs/5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/5.png -------------------------------------------------------------------------------- /imgs/6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/6.png -------------------------------------------------------------------------------- /imgs/7.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/7.jpg -------------------------------------------------------------------------------- /imgs/8.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/8.png -------------------------------------------------------------------------------- /imgs/9.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/imgs/9.png -------------------------------------------------------------------------------- /other_image/counter_sticks.py: -------------------------------------------------------------------------------- 1 | # _*_ coding: utf-8 _*_ 2 | __author__ = 'LelandYan' 3 | __date__ = '2019/5/19 10:08' 4 | 5 | import cv2 6 | import numpy as np 7 | import matplotlib.pyplot as plt 8 | from scipy import ndimage as ndi 9 | import skimage as sm 10 | from skimage import morphology 11 | from skimage.feature import peak_local_max 12 | from skimage.io import imshow 13 | from skimage.color import rgb2gray 14 | from skimage.filters.rank import median 15 | from skimage.measure import find_contours 16 | 17 | 18 | image = cv2.imread("./raw_data/processing_.png") 19 | image = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) 20 | ret, binary = cv2.threshold(image, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_TRIANGLE)#TRIANGLE法,，全局自适应阈值, 参数0可改为任意数字但不起作用，适用于单个波峰 21 | print("阈值：%s" % ret) 22 | rows,cols = image.shape 23 | labels = np.zeros([rows,cols]) 24 | for i in range(rows): 25 | for j in range(cols): 26 | if(image[i,j] > ret): 27 | labels[i,j] = 1 28 | else: 29 | labels[i,j] = 0 30 | thresh = median(labels, sm.morphology.disk(5)) 31 | cv2.namedWindow("hull", cv2.WINDOW_NORMAL) 32 | cv2.imshow('hull', thresh) 33 | cv2.waitKey(0) 34 | cv2.destroyAllWindows() 35 | 36 | 37 | 38 | # img = cv2.pyrDown(cv2.imread("./raw_data/4.jpg")) 39 | # # threshold 函数对图像进行二化值处理，由于处理后图像对原图像有所变化，因此img.copy()生成新的图像，cv2.THRESH_BINARY是二化值 40 | # ret, thresh = cv2.threshold(cv2.cvtColor(img.copy(), cv2.COLOR_BGR2GRAY), 127, 255, cv2.THRESH_BINARY) 41 | # # ret, thresh = cv2.threshold(cv2.cvtColor(img.copy(), cv2.COLOR_BGR2GRAY), 0, 255, cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU) 42 | # thresh = median(thresh, sm.morphology.disk(5)) 43 | # 44 | # 45 | # def watershed(img): 46 | # gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY) 47 | # ret, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU) 48 | # kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3)) 49 | # mb = cv2.morphologyEx(binary, cv2.MORPH_OPEN, kernel, iterations=2) 50 | # sure_bg = cv2.dilate(mb, kernel, iterations=3) 51 | # dist = cv2.distanceTransform(mb, cv2.DIST_L2, 3) 52 | # dist_output = cv2.normalize(dist, 0, 1.0, cv2.NORM_MINMAX) 53 | # ret, surface = cv2.threshold(dist, dist.max() * 0.6, 255, cv2.THRESH_BINARY) 54 | # surface_fg = np.uint8(surface) 55 | # unknown = cv2.subtract(sure_bg, surface_fg) 56 | # ref, markers = cv2.connectedComponents(sure_bg) 57 | # markers = markers + 1 58 | # markers[unknown == 255] = 0 59 | # markers = cv2.watershed(src, markers=markers) 60 | # src[markers == -1] = [0, 0, 255] 61 | # cv2.imshow("result", src) 62 | # 63 | # 64 | # src = cv2.imread("./raw_data/4.jpg") 65 | # cv2.namedWindow("hull", cv2.WINDOW_NORMAL) 66 | # cv2.imshow('def', src) 67 | # watershed(src) 68 | # cv2.waitKey(0) 69 | # cv2.destroyAllWindows() 70 | # 71 | # 72 | # 73 | # 74 | # 75 | # 76 | # 77 | # 78 | # 79 | # 80 | # 81 | # 82 | # # findContours函数查找图像里的图形轮廓 83 | # # 函数参数thresh是图像对象 84 | # # 层次类型，参数cv2.RETR_EXTERNAL是获取最外层轮廓，cv2.RETR_TREE是获取轮廓的整体结构 85 | # # 轮廓逼近方法 86 | # # 输出的返回值，image是原图像、contours是图像的轮廓、hier是层次类型 87 | # image, contours, hier = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) 88 | # 89 | # for c in contours: 90 | # # 轮廓绘制方法一 91 | # # boundingRect函数计算边框值，x，y是坐标值，w，h是矩形的宽和高 92 | # x, y, w, h = cv2.boundingRect(c) 93 | # # 在img图像画出矩形，(x, y), (x + w, y + h)是矩形坐标，(0, 255, 0)设置通道颜色，2是设置线条粗度 94 | # cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2) 95 | # 96 | # # 轮廓绘制方法二 97 | # # 查找最小区域 98 | # rect = cv2.minAreaRect(c) 99 | # # 计算最小面积矩形的坐标 100 | # box = cv2.boxPoints(rect) 101 | # # 将坐标规范化为整数 102 | # box = np.int0(box) 103 | # # 绘制矩形 104 | # cv2.drawContours(img, [box], 0, (0, 0, 255), 3) 105 | # 106 | # # 轮廓绘制方法三 107 | # # 圆心坐标和半径的计算 108 | # (x, y), radius = cv2.minEnclosingCircle(c) 109 | # # 规范化为整数 110 | # center = (int(x), int(y)) 111 | # radius = int(radius) 112 | # # 勾画圆形区域 113 | # img = cv2.circle(img, center, radius, (0, 255, 0), 2) 114 | # 115 | # # # 轮廓绘制方法四 116 | # # 围绕图形勾画蓝色线条 117 | # cv2.drawContours(img, contours, -1, (255, 0, 0), 2) 118 | # # 显示图像 119 | # cv2.imshow("contours", img) 120 | # cv2.waitKey() 121 | # cv2.destroyAllWindows() 122 | -------------------------------------------------------------------------------- /other_image/edge_cutting.py: -------------------------------------------------------------------------------- 1 | # _*_ coding: utf-8 _*_ 2 | __author__ = 'LelandYan' 3 | __date__ = '2019/5/19 10:58' 4 | import cv2 5 | import numpy as np 6 | import matplotlib.pyplot as plt 7 | from scipy import ndimage as ndi 8 | import skimage as sm 9 | from skimage import morphology 10 | from skimage.feature import peak_local_max 11 | from skimage.filters.rank import median 12 | 13 | 14 | image = cv2.imread("./raw_data/1.jpg") 15 | gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY) 16 | ret, thresh = cv2.threshold(gray,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU) 17 | # thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 25, 10) 18 | thresh = median(thresh, sm.morphology.disk(5)) 19 | 20 | # noise removal 21 | kernel = np.ones((3,3),np.uint8) 22 | opening = cv2.morphologyEx(thresh,cv2.MORPH_OPEN,kernel, iterations = 1) 23 | ###################################################################################### 24 | th, im_th = cv2.threshold(opening, 220, 255, cv2.THRESH_BINARY_INV) 25 | 26 | # Copy the thresholded image. 27 | im_floodfill = im_th.copy() 28 | 29 | # Mask used to flood filling. 30 | # Notice the size needs to be 2 pixels than the image. 31 | h, w = im_th.shape[:2] 32 | mask = np.zeros((h + 2, w + 2), np.uint8) 33 | 34 | # Floodfill from point (0, 0) 35 | cv2.floodFill(im_floodfill, mask, (0, 0), 255) 36 | 37 | opening = im_floodfill 38 | ########################################################################### 39 | # sure background area 40 | sure_bg = cv2.dilate(opening,kernel,iterations=6) 41 | 42 | 43 | # Finding sure foreground area 44 | dist_transform = cv2.distanceTransform(opening,cv2.DIST_L2,5) 45 | ret, sure_fg = cv2.threshold(dist_transform,0.7*dist_transform.max(),255,0) 46 | # Finding unknown region 47 | sure_fg = np.uint8(sure_fg) 48 | unknown = cv2.subtract(sure_bg,sure_fg) 49 | 50 | plt.imshow(sure_fg,'gray') 51 | 52 | 53 | cv2.namedWindow("binary2", cv2.WINDOW_NORMAL) 54 | cv2.imshow('binary2', opening) 55 | cv2.waitKey(0) 56 | cv2.destroyAllWindows() 57 | 58 | -------------------------------------------------------------------------------- /other_image/first_image.py: -------------------------------------------------------------------------------- 1 | # _*_ coding: utf-8 _*_ 2 | __author__ = 'LelandYan' 3 | __date__ = '2019/5/16 19:32' 4 | import numpy as np 5 | import cv2 6 | import matplotlib.pyplot as plt 7 | import copy 8 | from pylab import mpl 9 | 10 | # 防止中文乱码 11 | mpl.rcParams['font.sans-serif'] = ['SimHei'] 12 | 13 | 14 | class processing_image: 15 | def __init__(self, filename="./raw_data/timg.jpg", output="./out_data",icon="./raw_data/icon_timg.jpg"): 16 | self.filename = filename 17 | self.output = output 18 | self.icon = icon 19 | 20 | def op_gray_to_four_type(self, kernel=(9, 9), erode_iter=5, dilate_iter=5): 21 | 22 | img = cv2.imread(self.filename) 23 | # gray 24 | img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) 25 | # erode dilate 26 | closed = cv2.erode(img, None, iterations=erode_iter) 27 | img = cv2.dilate(closed, None, iterations=dilate_iter) 28 | 29 | kernel = np.ones(kernel, np.uint8) 30 | # open operation 31 | img_open = cv2.morphologyEx(img, op=cv2.MORPH_OPEN, kernel=kernel) 32 | # close operation 33 | img_close = cv2.morphologyEx(img, op=cv2.MORPH_CLOSE, kernel=kernel) 34 | # gradient operation 35 | img_grad = cv2.morphologyEx(img, op=cv2.MORPH_GRADIENT, kernel=kernel) 36 | # tophat operation 37 | img_tophat = cv2.morphologyEx(img, op=cv2.MORPH_TOPHAT, kernel=kernel) 38 | # blackhat operation 39 | img_blackhat = cv2.morphologyEx(img, op=cv2.MORPH_BLACKHAT, kernel=kernel) 40 | # Plot the images 41 | images = [img, img_open, img_close, img_grad, 42 | img_tophat, img_blackhat] 43 | names = ["raw_img", "img_open", "img_close", "img_grad", "img_tophat", "img_blackhat"] 44 | cv2.imwrite(self.output+"/gradient_image1.jpg",img_grad) 45 | fig, axs = plt.subplots(nrows=2, ncols=3, figsize=(15, 15)) 46 | for ind, p in enumerate(images): 47 | ax = axs[ind // 3, ind % 3] 48 | ax.imshow(p, cmap='gray') 49 | ax.set_title(names[ind]) 50 | ax.axis('off') 51 | plt.show() 52 | 53 | def op_first_to_three_type(self, flag=False): 54 | # 全局阈值 55 | def threshold_demo(image): 56 | gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) # 把输入图像灰度化 57 | # 直接阈值化是对输入的单通道矩阵逐像素进行阈值分割。 58 | ret, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_TRIANGLE) 59 | if flag: 60 | cv2.imwrite(self.output + "/global_binary_first1.jpg", binary) 61 | return binary 62 | 63 | # 局部阈值 64 | def local_threshold(image): 65 | gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) # 把输入图像灰度化 66 | # 自适应阈值化能够根据图像不同区域亮度分布，改变阈值 67 | binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 25, 10) 68 | if flag: 69 | cv2.imwrite(self.output + "/local_binary_first1.jpg", binary) 70 | return binary 71 | 72 | # 用户自己计算阈值 73 | def custom_threshold(image): 74 | gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) # 把输入图像灰度化 75 | h, w = gray.shape[:2] 76 | m = np.reshape(gray, [1, w * h]) 77 | mean = m.sum() / (w * h) 78 | ret, binary = cv2.threshold(gray, mean, 255, cv2.THRESH_BINARY) 79 | if flag: 80 | cv2.imwrite(self.output + "/custom_binary_first1.jpg", binary) 81 | return binary 82 | 83 | if flag: 84 | src = cv2.imread("./out_data/gradient_image1.jpg") 85 | else: 86 | src = cv2.imread(self.filename) 87 | src = cv2.cvtColor(src, cv2.COLOR_BGR2RGB) 88 | global_scr = threshold_demo(src) 89 | local_scr = local_threshold(src) 90 | custom_src = custom_threshold(src) 91 | images = [src, global_scr, local_scr, 92 | custom_src] 93 | names = ["src", "global_scr", "local_scr", "custom_src"] 94 | fig, axs = plt.subplots(nrows=2, ncols=2, figsize=(10, 10)) 95 | for ind, p in enumerate(images): 96 | ax = axs[ind // 2, ind % 2] 97 | ax.imshow(p, cmap='gray') 98 | ax.set_title(names[ind]) 99 | ax.axis('off') 100 | plt.show() 101 | 102 | def op_cutting_image(self): 103 | raw_img = cv2.imread(self.filename) 104 | img = cv2.imread("./out_data/gradient_image1.jpg") 105 | gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) 106 | blurred = cv2.bilateralFilter(gray, 7, sigmaSpace=75, sigmaColor=75) 107 | ret, binary = cv2.threshold(blurred, 127, 255, cv2.THRESH_BINARY) 108 | closed = cv2.dilate(binary, None, iterations=130) 109 | closed = cv2.erode(closed, None, iterations=127) 110 | 111 | _, contours, hierarchy = cv2.findContours(closed, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) 112 | c = sorted(contours, key=cv2.contourArea, reverse=True)[0] 113 | 114 | # compute the rotated bounding box of the largest contour 115 | rect = cv2.minAreaRect(c) 116 | box = np.int0(cv2.boxPoints(rect)) 117 | # draw a bounding box arounded the detected barcode and display the image 118 | draw_img = cv2.drawContours(raw_img.copy(), [box], -1, (0, 0, 255), 3) 119 | 120 | h, w, _ = img.shape 121 | Xs = [i[0] for i in box] 122 | Ys = [i[1] for i in box] 123 | x1 = min(Xs) 124 | x2 = max(Xs) 125 | y1 = min(Ys) 126 | y2 = max(Ys) 127 | hight = y2 - y1 128 | width = x2 - x1 129 | crop_img = img[0:h - hight, x1:x1 + width] 130 | raw_img = raw_img[0:h - hight, x1:x1 + width] 131 | cv2.imwrite(self.output + "/raw_draw_image1.jpg", draw_img) 132 | cv2.imwrite(self.output + "/raw_cutting_image1.jpg", raw_img) 133 | cv2.imwrite(self.output + "/gray_cutting_image1.jpg", crop_img) 134 | 135 | def op_edge_test(self): 136 | def gray_dege_test(): 137 | img = cv2.imread("./out_data/gradient_image1.jpg") 138 | gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) 139 | blurred = cv2.GaussianBlur(gray, (9, 9), 0) 140 | ret, binary = cv2.threshold(blurred, 127, 255, cv2.THRESH_BINARY) 141 | closed = cv2.dilate(binary, None, iterations=110) 142 | closed = cv2.erode(closed, None, iterations=120) 143 | 144 | _, contours, hierarchy = cv2.findContours(closed, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) 145 | 146 | cv2.drawContours(img, contours, -1, (0, 0, 255), 3) 147 | plt.imshow(img) 148 | plt.show() 149 | cv2.imwrite(self.output + "/gray_edge_test.jpg", img) 150 | 151 | def fourier_edge_test(): 152 | img = cv2.imread('./out_data/gradient_image1.jpg', 0) 153 | f = np.fft.fft2(img) 154 | fshift = np.fft.fftshift(f) 155 | 156 | rows, cols = img.shape 157 | crow, ccol = int(rows / 2), int(cols / 2) 158 | for i in range(crow - 30, crow + 30): 159 | for j in range(ccol - 30, ccol + 30): 160 | fshift[i][j] = 0.0 161 | f_ishift = np.fft.ifftshift(fshift) 162 | img_back = np.fft.ifft2(f_ishift) # 进行高通滤波 163 | # 取绝对值 164 | img_back = np.abs(img_back) 165 | plt.subplot(121), plt.imshow(img, cmap='gray') # 因图像格式问题，暂已灰度输出 166 | plt.title('Input Image'), plt.xticks([]), plt.yticks([]) 167 | # 先对灰度图像进行伽马变换，以提升暗部细节 168 | rows, cols = img_back.shape 169 | gamma = copy.deepcopy(img_back) 170 | rows = img.shape[0] 171 | cols = img.shape[1] 172 | for i in range(rows): 173 | for j in range(cols): 174 | gamma[i][j] = 5.0 * pow(gamma[i][j], 0.34) # 0.34这个参数是我手动调出来的，根据不同的图片，可以选择不同的数值 175 | # 对灰度图像进行反转 176 | 177 | for i in range(rows): 178 | for j in range(cols): 179 | gamma[i][j] = 255 - gamma[i][j] 180 | 181 | plt.subplot(122), plt.imshow(gamma, cmap='gray') 182 | plt.title('Result in HPF'), plt.xticks([]), plt.yticks([]) 183 | cv2.imwrite(self.output + "/fourier_edge_test_image1.jpg", gamma) 184 | plt.show() 185 | 186 | def canny_edge_test(): 187 | img = cv2.imread('./out_data/gradient_image1.jpg', 0) 188 | edges = cv2.Canny(img, 100, 200) 189 | 190 | plt.subplot(121), plt.imshow(img, cmap='gray') 191 | plt.title('original'), plt.xticks([]), plt.yticks([]) 192 | plt.subplot(122), plt.imshow(edges, cmap='gray') 193 | plt.title('edge'), plt.xticks([]), plt.yticks([]) 194 | cv2.imwrite(self.output + "/canny_edge_test_image1.jpg", edges) 195 | plt.show() 196 | 197 | gray_dege_test() 198 | fourier_edge_test() 199 | canny_edge_test() 200 | 201 | def op_trans_plot(self): 202 | im_in = cv2.imread("./out_data/global_binary_first1.jpg", cv2.IMREAD_GRAYSCALE) 203 | th, im_th = cv2.threshold(im_in, 220, 255, cv2.THRESH_BINARY_INV) 204 | 205 | # Copy the thresholded image. 206 | im_floodfill = im_th.copy() 207 | 208 | # Mask used to flood filling. 209 | # Notice the size needs to be 2 pixels than the image. 210 | h, w = im_th.shape[:2] 211 | mask = np.zeros((h + 2, w + 2), np.uint8) 212 | 213 | # Floodfill from point (0, 0) 214 | cv2.floodFill(im_floodfill, mask, (0, 0), 255) 215 | cv2.imwrite(self.output + "/edge_processing1.jpg", im_floodfill) 216 | 217 | def op_counter(self): 218 | ob1 = cv2.imread("./out_data/edge_processing1.jpg", cv2.IMREAD_GRAYSCALE) 219 | # ob1 = cv2.dilate(ob1, None, iterations=2) 220 | ob1 = cv2.bilateralFilter(ob1, 7, sigmaSpace=70, sigmaColor=70) 221 | ob1 = cv2.erode(ob1, None, iterations=2) # 1 # 2 222 | ob1 = cv2.dilate(ob1, None, iterations=2) 223 | ob2 = cv2.imread(self.icon, cv2.IMREAD_GRAYSCALE) 224 | # ob2 = cv2.bilateralFilter(ob2, 7, sigmaSpace=60, sigmaColor=60) 225 | ob2 = cv2.erode(ob2, None, iterations=1) 226 | # ob2 = cv2.dilate(ob2, None, iterations=1) 227 | # orb = cv2.xfeatures2d.SURF_create() 228 | orb = cv2.xfeatures2d.SIFT_create() 229 | keyp1, desp1 = orb.detectAndCompute(ob1, None) 230 | keyp2, desp2 = orb.detectAndCompute(ob2, None) 231 | FLANN_INDEX_KDTREE = 1 232 | index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5) 233 | search_params = dict(checks=50) 234 | flann = cv2.FlannBasedMatcher(index_params, search_params) 235 | matches = flann.knnMatch(desp1, desp2, k=2) 236 | matchesMask = [[0, 0] for i in range(len(matches))] 237 | for i, (m, n) in enumerate(matches): 238 | if m.distance < 0.7 * n.distance: 239 | matchesMask[i] = [1, 0] 240 | # 如果第一个邻近距离比第二个邻近距离的0.7倍小，则保留 241 | draw_params = dict(matchColor=(0, 255, 0), singlePointColor=(255, 0, 0), matchesMask=matchesMask, flags=0) 242 | img3 = cv2.drawMatchesKnn(ob1, keyp1, ob2, keyp2, matches, None, **draw_params) 243 | a = len(keyp1) // len(keyp2) 244 | plt.figure(figsize=(8, 8)) 245 | plt.subplot(211) 246 | plt.imshow(img3) 247 | plt.subplot(212) 248 | plt.text(0.5, 0.6, "the number of sticks:" + str(a), size=30, ha="center", va="center") 249 | plt.axis('off') 250 | plt.show() 251 | cv2.imwrite(self.output+"/counter_sticks_image1.jpg", img3) 252 | 253 | if __name__ == '__main__': 254 | ob = processing_image(filename="./raw_data/timber4.jpg",icon="./raw_data/icon_timgber4.png") 255 | ob.op_gray_to_four_type() 256 | ob.op_first_to_three_type() 257 | # ob.op_cutting_image() 258 | ob.op_edge_test() 259 | ob.op_first_to_three_type(flag=True) 260 | ob.op_trans_plot() 261 | ob.op_counter() 262 | -------------------------------------------------------------------------------- /other_image/last_test.py: -------------------------------------------------------------------------------- 1 | # _*_ coding: utf-8 _*_ 2 | __author__ = 'LelandYan' 3 | __date__ = '2019/5/19 16:22' 4 | 5 | import cv2 6 | import matplotlib.pyplot as plt 7 | import numpy as np 8 | 9 | img = cv2.imread("aaaaaaaa.jpg") 10 | # img = cv2.cvtColor(img,cv2.COLOR_RGB2GRAY) 11 | img_hls = cv2.cvtColor(img, cv2.COLOR_BGR2HLS) 12 | # cv2.namedWindow("hull", cv2.WINDOW_NORMAL) 13 | # cv2.imshow("hull", img) 14 | # cv2.waitKey() 15 | # cv2.destroyAllWindows() 16 | from scipy import ndimage as ndi 17 | 18 | img = img[:, :, 0] 19 | plt.figure('hist_plot') 20 | arr = img.flatten() 21 | plt.hist(arr, 256) 22 | plt.show() 23 | 24 | rows, cols = img.shape 25 | labels = np.zeros([rows, cols]) 26 | for i in range(rows): 27 | for j in range(cols): 28 | if (img[i, j] > 70): 29 | labels[i, j] = 1 30 | else: 31 | labels[i, j] = 0 32 | 33 | cv2.namedWindow("labels", cv2.WINDOW_NORMAL) 34 | cv2.imshow("labels", labels) 35 | cv2.waitKey(0) 36 | cv2.destroyAllWindows() 37 | -------------------------------------------------------------------------------- /other_image/main.py: -------------------------------------------------------------------------------- 1 | # _*_ coding: utf-8 _*_ 2 | __author__ = 'LelandYan' 3 | __date__ = '2019/5/19 7:42' 4 | 5 | import cv2 6 | import numpy as np 7 | import matplotlib.pyplot as plt 8 | from scipy import ndimage as ndi 9 | import skimage as sm 10 | from skimage import morphology 11 | from skimage.feature import peak_local_max 12 | from skimage.io import imshow 13 | from skimage.color import rgb2gray 14 | from skimage.filters.rank import median 15 | from skimage.measure import find_contours 16 | 17 | 18 | # image = cv2.imread("./raw_data/1.jpg") 19 | # dst = cv2.fastNlMeansDenoisingColored(image,None,10,10,7,21) 20 | # img = cv2.pyrDown(dst, cv2.IMREAD_UNCHANGED) 21 | # # ret, thresh = cv2.threshold(cv2.cvtColor(img.copy(), cv2.COLOR_BGR2GRAY) , 127, 255, cv2.THRESH_BINARY) 22 | # thresh = cv2.adaptiveThreshold(cv2.cvtColor(img.copy(), cv2.COLOR_BGR2GRAY), 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 25, 10) 23 | # thresh = median(thresh, sm.morphology.disk(5)) 24 | # cv2.namedWindow("thresh", cv2.WINDOW_NORMAL) 25 | # cv2.imshow("thresh", thresh) 26 | # cv2.waitKey() 27 | # cv2.destroyAllWindows() 28 | ################################################################### 29 | 30 | ################################################################## 31 | # kernel = np.ones((3,3),np.uint8) 32 | # opening = cv2.morphologyEx(thresh,cv2.MORPH_OPEN,kernel, iterations = 1) 33 | 34 | # threshold, imgOtsu = cv2.threshold(thresh, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU) 35 | # cv2.namedWindow("hull", cv2.WINDOW_NORMAL) 36 | # cv2.imshow("hull", imgOtsu) 37 | # cv2.waitKey() 38 | # cv2.destroyAllWindows() 39 | # cv2.namedWindow("hull", cv2.WINDOW_NORMAL) 40 | # cv2.imshow("hull", thresh) 41 | # cv2.waitKey() 42 | # cv2.destroyAllWindows() 43 | # findContours函数查找图像里的图形轮廓 44 | # 函数参数thresh是图像对象 45 | # 层次类型，参数cv2.RETR_EXTERNAL是获取最外层轮廓，cv2.RETR_TREE是获取轮廓的整体结构 46 | # 轮廓逼近方法 47 | # 输出的返回值，image是原图像、contours是图像的轮廓、hier是层次类型 48 | ######################################################################################### 49 | image = cv2.imread("./raw_data/4.jpg") 50 | gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY) 51 | 52 | ret, thresh = cv2.threshold(gray,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU) 53 | # thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 25, 10) 54 | 55 | 56 | # noise removal 57 | kernel = np.ones((3,3),np.uint8) 58 | opening = cv2.morphologyEx(thresh,cv2.MORPH_OPEN,kernel, iterations = 1) 59 | opening = cv2.bilateralFilter(opening,9,80,80) 60 | opening = median(opening, sm.morphology.disk(3)) 61 | # opening = cv2.morphologyEx(opening,cv2.MORPH_GRADIENT,kernel, iterations = 1) 62 | ###################################################################################### 63 | th, im_th = cv2.threshold(opening, 220, 255, cv2.THRESH_BINARY_INV) 64 | # sure_bg = cv2.dilate(opening,kernel,iterations=2) 65 | # Copy the thresholded image. 66 | im_floodfill = im_th.copy() 67 | 68 | # Mask used to flood filling. 69 | # Notice the size needs to be 2 pixels than the image. 70 | h, w = im_th.shape[:2] 71 | mask = np.zeros((h + 2, w + 2), np.uint8) 72 | 73 | # Floodfill from point (0, 0) 74 | cv2.floodFill(im_floodfill, mask, (0, 0), 255) 75 | 76 | opening = im_floodfill 77 | opening = cv2.erode(opening,kernel,iterations=7) 78 | ######################################################################################### 79 | image, contours, hier = cv2.findContours(opening, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) 80 | # 创建新的图像black 81 | black = cv2.cvtColor(np.zeros((image.shape[1], image.shape[0]), dtype=np.uint8), cv2.COLOR_GRAY2BGR) 82 | 83 | counter = 0 84 | for p,cnt in enumerate(contours): 85 | 86 | area = cv2.contourArea(contours[p]) 87 | if area < 30: 88 | print("$$$$") 89 | continue 90 | # 轮廓周长也被称为弧长。可以使用函数 cv2.arcLength() 计算得到。这个函数的第二参数可以用来指定对象的形状是闭合的（True） ，还是打开的（一条曲线） 91 | epsilon = 0.01 * cv2.arcLength(cnt, True) 92 | # 函数approxPolyDP来对指定的点集进行逼近，cnt是图像轮廓，epsilon表示的是精度，越小精度越高，因为表示的意思是是原始曲线与近似曲线之间的最大距离。 93 | # 第三个函数参数若为true,则说明近似曲线是闭合的，它的首位都是相连，反之，若为false，则断开。 94 | approx = cv2.approxPolyDP(cnt, epsilon, True) 95 | # convexHull检查一个曲线的凸性缺陷并进行修正，参数cnt是图像轮廓。 96 | hull = cv2.convexHull(cnt) 97 | # 勾画图像原始的轮廓 98 | cv2.drawContours(black, [cnt], -1, (0, 255, 0), 2) 99 | # 用多边形勾画轮廓区域 100 | cv2.drawContours(black, [approx], -1, (255, 255, 0), 2) 101 | # 修正凸性缺陷的轮廓区域 102 | cv2.drawContours(black, [hull], -1, (0, 0, 255), 2) 103 | counter+=1 104 | # 显示图像 105 | print(counter) 106 | plt.imshow(black) 107 | 108 | cv2.namedWindow("hull", cv2.WINDOW_NORMAL) 109 | cv2.imshow("hull", black) 110 | cv2.waitKey() 111 | cv2.destroyAllWindows() 112 | from scipy import ndimage as ndi 113 | # labels = dst 114 | distance = ndi.distance_transform_edt(opening) #距离变换 115 | # min_distance：最小的像素在2×min_distance + 1区分离（即峰峰数至少min_distance分隔）。找到峰值的最大数量，使用min_distance = 1。 116 | # exclude_border：不排除峰值在图像的边界 117 | # indices：False会返回和数组相同大小的布尔数组，为True时，会返回峰值的坐标 118 | local_maxi =peak_local_max(distance, exclude_border = 0,min_distance = 12,indices=False, 119 | footprint=np.ones((10, 10)),labels=opening) #寻找峰值 120 | markers = ndi.label(local_maxi)[0] #初始标记点 121 | label_ =morphology.watershed(-distance, markers, mask=opening) #基于距离变换的分水岭算法 122 | 123 | fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(12, 12)) 124 | axes = axes.ravel() 125 | ax0, ax1, ax2, ax3 = axes 126 | 127 | ax0.imshow(opening, cmap=plt.cm.gray)#, interpolation='nearest') 128 | ax0.set_title("Original") 129 | ax1.imshow(-distance, cmap=plt.cm.jet, interpolation='nearest') 130 | ax1.set_title("Distance") 131 | ax2.imshow(sm.morphology.dilation(markers,sm.morphology.square(10)), cmap=plt.cm.Spectral, interpolation='nearest') 132 | ax2.set_title("Markers") 133 | ax3.imshow(label_, cmap=plt.cm.Spectral, interpolation='nearest') 134 | ax3.set_title("Segmented") 135 | for ax in axes: 136 | ax.axis('off') 137 | 138 | fig.tight_layout() 139 | plt.show() 140 | -------------------------------------------------------------------------------- /other_image/other_image.py: -------------------------------------------------------------------------------- 1 | # _*_ coding: utf-8 _*_ 2 | __author__ = 'LelandYan' 3 | __date__ = '2019/5/17 18:55' 4 | 5 | import cv2 6 | import numpy as np 7 | import matplotlib.pyplot as plt 8 | from scipy import ndimage as ndi 9 | import skimage as sm 10 | from skimage import morphology 11 | from skimage.feature import peak_local_max 12 | from skimage.filters.rank import median 13 | image = cv2.imread("./raw_data/4.jpg") 14 | kernel_sharpen_1 = np.array([ 15 | [-1,-1,-1], 16 | [-1,9,-1], 17 | [-1,-1,-1]]) 18 | kernel_sharpen_2 = np.array([ 19 | [1,1,1], 20 | [1,-7,1], 21 | [1,1,1]]) 22 | kernel_sharpen_3 = np.array([ 23 | [-1,-1,-1,-1,-1], 24 | [-1,2,2,2,-1], 25 | [-1,2,8,2,-1], 26 | [-1,2,2,2,-1], 27 | [-1,-1,-1,-1,-1]])/8.0 28 | 29 | output_1 = cv2.filter2D(image,-1,kernel_sharpen_3) 30 | # output_2 = cv2.filter2D(image,-1,kernel_sharpen_2) 31 | # output_3 = cv2.filter2D(image,-1,kernel_sharpen_3) 32 | # 显示锐化效果 33 | # cv2.namedWindow('Original Image', cv2.WINDOW_NORMAL) 34 | # cv2.imwrite('Original_Image1.jpg',image) 35 | # cv2.namedWindow('sharpen_1 Image', cv2.WINDOW_NORMAL) 36 | # cv2.imwrite('./out_data/sharpen_1_Image1.jpg',output_1) 37 | # cv2.namedWindow('sharpen_2 Image', cv2.WINDOW_NORMAL) 38 | # cv2.imwrite('./out_data/sharpen_2_Image1.jpg',output_2) 39 | # cv2.namedWindow('sharpen_3 Image', cv2.WINDOW_NORMAL) 40 | # cv2.imwrite('./out_data/sharpen_3_Image1.jpg',output_3) 41 | 42 | 43 | output_1 = cv2.cvtColor(output_1, cv2.COLOR_RGB2GRAY) # 把输入图像灰度化 44 | # output_2 = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) #把输入图像灰度化 45 | # output_3 = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) #把输入图像灰度化 46 | 47 | # cv2.namedWindow('im_floodfill', 0) 48 | # cv2.imshow("im_floodfill", output_1) 49 | # 50 | # cv2.waitKey(0) 51 | # cv2.destroyAllWindows() 52 | 53 | 54 | 55 | # cv2.namedWindow('sharpen_1 Image', cv2.WINDOW_NORMAL) 56 | # cv2.imwrite('./out_data/gray_sharpen_1_Image1.jpg',output_1) 57 | # # cv2.namedWindow('sharpen_2 Image', cv2.WINDOW_NORMAL) 58 | # cv2.imwrite('./out_data/gray_sharpen_2_Image1.jpg',output_2) 59 | # # cv2.namedWindow('sharpen_3 Image', cv2.WINDOW_NORMAL) 60 | # cv2.imwrite('./out_data/gray_sharpen_3_Image1.jpg',output_3) 61 | 62 | # 63 | plt.hist(output_1.ravel(),256) 64 | plt.show() 65 | ret, binary = cv2.threshold(output_1, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_TRIANGLE)#TRIANGLE法,，全局自适应阈值, 参数0可改为任意数字但不起作用，适用于单个波峰 66 | print("阈值：%s" % ret) 67 | # cv2.namedWindow("binary0", cv2.WINDOW_NORMAL) 68 | # #cv.imwrite("binary_first11.jpg", binary) 69 | # cv2.imshow("binary0", binary) 70 | # cv2.waitKey(0) 71 | # cv2.destroyAllWindows() 72 | rows,cols = output_1.shape 73 | labels = np.zeros([rows,cols]) 74 | for i in range(rows): 75 | for j in range(cols): 76 | if(output_1[i,j] > ret): 77 | labels[i,j] = 1 78 | else: 79 | labels[i,j] = 0 80 | 81 | # cv2.namedWindow("labels", cv2.WINDOW_NORMAL) 82 | # cv2.imwrite("aaaa.jpg", labels) 83 | # cv2.imshow("labels", labels) 84 | # cv2.waitKey(0) 85 | # cv2.destroyAllWindows() 86 | # 87 | # # 88 | labels = median(labels, sm.morphology.disk(5)) 89 | distance = ndi.distance_transform_edt(labels) #距离变换 90 | # min_distance：最小的像素在2×min_distance + 1区分离（即峰峰数至少min_distance分隔）。找到峰值的最大数量，使用min_distance = 1。 91 | # exclude_border：不排除峰值在图像的边界 92 | # indices：False会返回和数组相同大小的布尔数组，为True时，会返回峰值的坐标 93 | local_maxi = peak_local_max(distance, exclude_border = 0,min_distance = 12,indices=False, 94 | footprint=np.ones((10, 10)),labels=labels) #寻找峰值 95 | markers = ndi.label(local_maxi)[0] #初始标记点 96 | label_ =morphology.watershed(-distance, markers, mask=labels) #基于距离变换的分水岭算法 97 | 98 | fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(12, 12)) 99 | axes = axes.ravel() 100 | ax0, ax1, ax2, ax3 = axes 101 | 102 | ax0.imshow(labels, cmap=plt.cm.gray)#, interpolation='nearest') 103 | ax0.set_title("Original") 104 | ax1.imshow(-distance, cmap=plt.cm.jet, interpolation='nearest') 105 | ax1.set_title("Distance") 106 | ax2.imshow(sm.morphology.dilation(markers,sm.morphology.square(10)), cmap= plt.cm.Spectral, interpolation='nearest') 107 | ax2.set_title("Markers") 108 | plt.imshow(label_, cmap= plt.cm.Spectral, interpolation='nearest') 109 | print(label_.shape) 110 | ax3.set_title("Segmented") 111 | 112 | for ax in axes: 113 | ax.axis('off') 114 | 115 | fig.tight_layout() 116 | plt.show() 117 | 118 | 119 | 120 | # import math 121 | # err = [] 122 | # import math 123 | # err = [] 124 | # for i in range(binary.shape[0]): 125 | # h1,w1 = binary[i][0],binary[i][1] 126 | # if i in err: 127 | # continue 128 | # for j in range(i+1,binary.shape[0]): 129 | # h2,w2 = binary[j][0],binary[j][1] 130 | # ab = math.sqrt(math.pow(abs(h2-h1), 2) + math.pow(abs(w2-w1), 2)) 131 | # if ab <= 10: 132 | # # print 'error:' , x_y[i],' and ', x_y[j],'i,j = ',i,j 133 | # err.append(j) 134 | # new_x_y = [] 135 | # for i in range(len(binary)): 136 | # if i not in err: 137 | # new_x_y.append(binary[i]) 138 | # print('一共有',len(binary),'个圈') 139 | # 140 | # 141 | # # def threshold_demo(image): 142 | # # gray = image 143 | # # # gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) #把输入图像灰度化 144 | # # #直接阈值化是对输入的单通道矩阵逐像素进行阈值分割。 145 | # # ret, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_TRIANGLE) 146 | # # print("threshold value %s"%ret) 147 | # # cv2.namedWindow("binary0", cv2.WINDOW_NORMAL) 148 | # # #cv.imwrite("binary_first11.jpg", binary) 149 | # # cv2.imshow("binary0", binary) 150 | # # 151 | # # #局部阈值 152 | # # def local_threshold(image): 153 | # # gray = image 154 | # # # gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) #把输入图像灰度化 155 | # # #自适应阈值化能够根据图像不同区域亮度分布，改变阈值 156 | # # binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,cv2.THRESH_BINARY, 25, 10) 157 | # # cv2.namedWindow("binary1", cv2.WINDOW_NORMAL) 158 | # # #cv.imwrite("binary_first22.jpg", binary) 159 | # # cv2.imshow("binary1", binary) 160 | # # 161 | # # #用户自己计算阈值 162 | # # def custom_threshold(image): 163 | # # gray = image 164 | # # # gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) #把输入图像灰度化 165 | # # h, w =gray.shape[:2] 166 | # # m = np.reshape(gray, [1,w*h]) 167 | # # mean = m.sum()/(w*h) 168 | # # print("mean:",mean) 169 | # # ret, binary = cv2.threshold(gray, mean, 255, cv2.THRESH_BINARY) 170 | # # #cv.imwrite("binary_first33.jpg", binary) 171 | # # cv2.namedWindow("binary2", cv2.WINDOW_NORMAL) 172 | # # cv2.imshow("binary2", binary) 173 | # # 174 | # # # src = cv2.imread(output_1) 175 | # # src = output_3 176 | # # cv2.namedWindow('input_image', cv2.WINDOW_NORMAL) #设置为WINDOW_NORMAL可以任意缩放 177 | # # cv2.imshow('input_image', src) 178 | # # 179 | # # threshold_demo(src) 180 | # # local_threshold(src) 181 | # # custom_threshold(src) 182 | # # cv2.waitKey(0) 183 | # # cv2.destroyAllWindows() 184 | -------------------------------------------------------------------------------- /other_image/out_data/canny_edge_test_image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/canny_edge_test_image1.jpg -------------------------------------------------------------------------------- /other_image/out_data/counter_sticks_image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/counter_sticks_image1.jpg -------------------------------------------------------------------------------- /other_image/out_data/custom_binary_first1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/custom_binary_first1.jpg -------------------------------------------------------------------------------- /other_image/out_data/edge_processing1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/edge_processing1.jpg -------------------------------------------------------------------------------- /other_image/out_data/fourier_edge_test_image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/fourier_edge_test_image1.jpg -------------------------------------------------------------------------------- /other_image/out_data/global_binary_first1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/global_binary_first1.jpg -------------------------------------------------------------------------------- /other_image/out_data/gradient_image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/gradient_image1.jpg -------------------------------------------------------------------------------- /other_image/out_data/gray_edge_test.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/gray_edge_test.jpg -------------------------------------------------------------------------------- /other_image/out_data/gray_sharpen_1_Image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/gray_sharpen_1_Image1.jpg -------------------------------------------------------------------------------- /other_image/out_data/gray_sharpen_2_Image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/gray_sharpen_2_Image1.jpg -------------------------------------------------------------------------------- /other_image/out_data/gray_sharpen_3_Image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/gray_sharpen_3_Image1.jpg -------------------------------------------------------------------------------- /other_image/out_data/local_binary_first1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/local_binary_first1.jpg -------------------------------------------------------------------------------- /other_image/out_data/sharpen_1_Image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/sharpen_1_Image1.jpg -------------------------------------------------------------------------------- /other_image/out_data/sharpen_2_Image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/sharpen_2_Image1.jpg -------------------------------------------------------------------------------- /other_image/out_data/sharpen_3_Image1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/out_data/sharpen_3_Image1.jpg -------------------------------------------------------------------------------- /other_image/raw_data/1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/1.jpg -------------------------------------------------------------------------------- /other_image/raw_data/2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/2.jpg -------------------------------------------------------------------------------- /other_image/raw_data/3.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/3.jpg -------------------------------------------------------------------------------- /other_image/raw_data/4.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/4.jpg -------------------------------------------------------------------------------- /other_image/raw_data/5.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/5.jpg -------------------------------------------------------------------------------- /other_image/raw_data/6.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/6.jpg -------------------------------------------------------------------------------- /other_image/raw_data/7.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/7.jpg -------------------------------------------------------------------------------- /other_image/raw_data/icon10.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/icon10.png -------------------------------------------------------------------------------- /other_image/raw_data/icon11.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/icon11.png -------------------------------------------------------------------------------- /other_image/raw_data/icon_timg.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/icon_timg.jpg -------------------------------------------------------------------------------- /other_image/raw_data/icon_timgber4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/icon_timgber4.png -------------------------------------------------------------------------------- /other_image/raw_data/mucai-003 (1).jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/mucai-003 (1).jpg -------------------------------------------------------------------------------- /other_image/raw_data/processing_.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/processing_.png -------------------------------------------------------------------------------- /other_image/raw_data/timber4.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/timber4.jpg -------------------------------------------------------------------------------- /other_image/raw_data/timg.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/other_image/raw_data/timg.jpg -------------------------------------------------------------------------------- /other_image/test2.py: -------------------------------------------------------------------------------- 1 | # _*_ coding: utf-8 _*_ 2 | __author__ = 'LelandYan' 3 | __date__ = '2019/5/19 7:23' 4 | 5 | import cv2 6 | import numpy as np 7 | import matplotlib.pyplot as plt 8 | from scipy import ndimage as ndi 9 | import skimage as sm 10 | from skimage import morphology 11 | from skimage.feature import peak_local_max 12 | from skimage.io import imshow 13 | from skimage.color import rgb2gray 14 | from skimage.filters.rank import median 15 | from skimage.measure import find_contours 16 | # image = cv2.imread("./raw_data/1.jpg") 17 | # cv2.imwrite("canny.jpg", cv2.Canny(image, 200, 300)) 18 | # cv2.namedWindow("canny", cv2.WINDOW_NORMAL) 19 | # cv2.imshow("canny", cv2.imread("canny.jpg")) 20 | # cv2.waitKey() 21 | # cv2.destroyAllWindows() 22 | 23 | img = cv2.pyrDown(cv2.imread("./raw_data/1.jpg", cv2.IMREAD_UNCHANGED)) 24 | # threshold 函数对图像进行二化值处理，由于处理后图像对原图像有所变化，因此img.copy()生成新的图像，cv2.THRESH_BINARY是二化值 25 | # ret, thresh = cv2.threshold(cv2.cvtColor(img.copy(), cv2.COLOR_BGR2GRAY), 127, 255, cv2.THRESH_BINARY) 26 | ret, thresh = cv2.threshold(cv2.cvtColor(img.copy(), cv2.COLOR_BGR2GRAY),0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU) 27 | thresh = median(thresh, sm.morphology.disk(5)) 28 | kernel = np.ones((3, 3), np.uint8) 29 | opening = cv2.morphologyEx(thresh, op= cv2.MORPH_OPEN,kernel=kernel,iterations=1) 30 | # sure_bg = cv2.dilate(opening,kernel,iterations=3)#膨胀 31 | # cv2.namedWindow("thresh", cv2.WINDOW_NORMAL) 32 | # cv2.imshow("thresh", opening) 33 | # cv2.waitKey() 34 | # cv2.destroyAllWindows() 35 | 36 | # findContours函数查找图像里的图形轮廓 37 | # 函数参数thresh是图像对象 38 | # 层次类型，参数cv2.RETR_EXTERNAL是获取最外层轮廓，cv2.RETR_TREE是获取轮廓的整体结构 39 | # 轮廓逼近方法 40 | # 输出的返回值，image是原图像、contours是图像的轮廓、hier是层次类型 41 | image, contours, hier = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) 42 | 43 | for c in contours: 44 | # 轮廓绘制方法一 45 | # boundingRect函数计算边框值，x，y是坐标值，w，h是矩形的宽和高 46 | # x, y, w, h = cv2.boundingRect(c) 47 | # # 在img图像画出矩形，(x, y), (x + w, y + h)是矩形坐标，(0, 255, 0)设置通道颜色，2是设置线条粗度 48 | # cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2) 49 | 50 | # 轮廓绘制方法二 51 | # 查找最小区域 52 | # rect = cv2.minAreaRect(c) 53 | # # 计算最小面积矩形的坐标 54 | # box = cv2.boxPoints(rect) 55 | # # 将坐标规范化为整数 56 | # box = np.int0(box) 57 | # # 绘制矩形 58 | # cv2.drawContours(img, [box], 0, (0, 0, 255), 3) 59 | 60 | # 轮廓绘制方法三 61 | # 圆心坐标和半径的计算 62 | (x, y), radius = cv2.minEnclosingCircle(c) 63 | # 规范化为整数 64 | center = (int(x), int(y)) 65 | radius = int(radius) 66 | # 勾画圆形区域 67 | img = cv2.circle(img, center, radius, (0, 255, 0), 2) 68 | 69 | # # 轮廓绘制方法四 70 | # 围绕图形勾画蓝色线条 71 | cv2.drawContours(img, contours, -1, (255, 0, 0), 2) 72 | print(len(contours)) 73 | # 显示图像 74 | cv2.imshow("contours", img) 75 | cv2.waitKey() 76 | cv2.destroyAllWindows() 77 | 78 | -------------------------------------------------------------------------------- /other_image/test4.py: -------------------------------------------------------------------------------- 1 | # _*_ coding: utf-8 _*_ 2 | __author__ = 'LelandYan' 3 | __date__ = '2019/5/19 7:47' 4 | 5 | import cv2 6 | import numpy as np 7 | import matplotlib.pyplot as plt 8 | from scipy import ndimage as ndi 9 | import skimage as sm 10 | from skimage import morphology 11 | from skimage.feature import peak_local_max 12 | from skimage.io import imshow 13 | from skimage.color import rgb2gray 14 | from skimage.filters.rank import median 15 | from skimage.measure import find_contours 16 | 17 | ################################################################################ 18 | 19 | print('Load Image') 20 | 21 | imgFile = './raw_data/1.jpg' 22 | 23 | # load an original image 24 | img = cv2.imread(imgFile) 25 | ################################################################################ 26 | 27 | # color value range 28 | cRange = 256 29 | 30 | rows, cols, channels = img.shape 31 | 32 | # convert color space from bgr to gray 33 | img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) 34 | imgGray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) 35 | ################################################################################ 36 | thresh = median(imgGray, sm.morphology.disk(5)) 37 | kernel = np.ones((3, 3), np.uint8) 38 | thresh = cv2.erode(thresh,kernel,iterations=3)#膨胀 39 | # laplacian edge 40 | imgLap = cv2.Laplacian(thresh, cv2.CV_8U) 41 | 42 | # otsu method 43 | threshold, imgOtsu = cv2.threshold(thresh, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU) 44 | 45 | # adaptive gaussian threshold 46 | imgAdapt = cv2.adaptiveThreshold(thresh, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 11, 2) 47 | # imgAdapt = cv2.medianBlur(imgAdapt, 3) 48 | ################################################################################ 49 | 50 | canny = cv2.Canny(imgAdapt, 10, 20) 51 | # 霍夫变换圆检测 52 | circles = cv2.HoughCircles(canny, cv2.HOUGH_GRADIENT, 1, 50, param1=80, param2=30, minRadius=0, maxRadius=50) 53 | # 输出返回值，方便查看类型 54 | # print(circles) 55 | 56 | # # 输出检测到圆的个数 57 | print(len(circles[0])) 58 | # 59 | # print('-------------我是条分割线-----------------') 60 | # 根据检测到圆的信息，画出每一个圆 61 | for circle in circles[0]: 62 | # 圆的基本信息 63 | print(circle[2]) 64 | # 坐标行列(就是圆心) 65 | x = int(circle[0]) 66 | y = int(circle[1]) 67 | # 半径 68 | r = int(circle[2]) 69 | # 在原图用指定颜色圈出圆，参数设定为int所以圈画存在误差 70 | img = cv2.circle(img, (x, y), r, (255, 255,255), 1, 8, 0) 71 | # 显示新图像 72 | cv2.namedWindow("binary2", cv2.WINDOW_NORMAL) 73 | cv2.imshow('binary2', img) 74 | 75 | # 按任意键退出 76 | cv2.waitKey(0) 77 | cv2.destroyAllWindows() 78 | 79 | 80 | 81 | 82 | 83 | 84 | # display original image and gray image 85 | # plt.subplot(2, 2, 1), plt.imshow(img), plt.title('Original Image'), plt.xticks([]), plt.yticks([]) 86 | # plt.subplot(2, 2, 2), plt.imshow(imgLap, cmap='gray'), plt.title('Laplacian Edge'), plt.xticks([]), plt.yticks([]) 87 | # plt.subplot(2, 2, 3), plt.imshow(imgOtsu, cmap='gray'), plt.title('Otsu Method'), plt.xticks([]), plt.yticks([]) 88 | # plt.subplot(2, 2, 4), plt.imshow(imgAdapt, cmap='gray'), plt.title('Adaptive Gaussian Threshold'), plt.xticks( 89 | # []), plt.yticks([]) 90 | # plt.show() 91 | # ################################################################################ 92 | # 93 | # print('Goodbye!') -------------------------------------------------------------------------------- /other_image/分水岭.py: -------------------------------------------------------------------------------- 1 | # _*_ coding: utf-8 _*_ 2 | __author__ = 'LelandYan' 3 | __date__ = '2019/5/19 10:25' 4 | 5 | import cv2 as cv 6 | import numpy as np 7 | 8 | def water_shed(image): 9 | #1 去噪，灰度，二值化 10 | blurred = cv.pyrMeanShiftFiltering(image,10,30) 11 | blurred=cv.bilateralFilter(image,0,50,5) 12 | # cv.imshow('blurred',blurred) 13 | gray=cv.cvtColor(blurred,cv.COLOR_BGR2GRAY) 14 | ret,binary=cv.threshold(gray,0,255,cv.THRESH_BINARY|cv.THRESH_OTSU) 15 | # cv.imshow('binary',binary) 16 | #2. mophology 开操作去除噪点 17 | kernel=cv.getStructuringElement(cv.MORPH_RECT,(3,3)) 18 | open_binary=cv.morphologyEx(binary,cv.MORPH_OPEN,kernel,iterations=2) #mophology binary,2次开操作 19 | # cv.imshow('1-open-op',open_binary) 20 | dilate_bg=cv.dilate(open_binary,kernel,iterations=3) #3次膨胀 21 | # cv.imshow('2-dilate-op',dilate_bg) 22 | #3.distance transform 23 | # DIST_L1:曼哈顿距离，DIST_L2：欧氏距离,masksize:跟卷积一样 24 | dist=cv.distanceTransform(open_binary,cv.DIST_L2,3) #？？ 25 | dist_norm=cv.normalize(dist,0,1.0,cv.NORM_MINMAX)# 0-1之间标准化 26 | # cv.imshow('3-distance-t',dist_norm*50) 27 | 28 | ret,surface=cv.threshold(dist,dist.max()*0.65,255,cv.THRESH_BINARY) 29 | # cv.imshow('4-surface',surface) 30 | 31 | #4计算marker 32 | surface_fg=np.uint8(surface) #计算前景 33 | unknown=cv.subtract(dilate_bg,surface_fg) #计算未知区域 34 | # cv.imshow('5-unknown',unknown) 35 | ret,markers=cv.connectedComponents(surface_fg) #通过计算cc，计算markers 36 | print(ret) 37 | # cv.imshow('6-markers',markers) 38 | 39 | #5 watershed 分水岭变换 40 | markers=markers+1 #用label进行控制 41 | markers[unknown==255]=0 42 | markers=cv.watershed(image,markers) #分水岭的地方就编程-1 43 | image[markers==-1]=[0,0,255] 44 | cv.imshow('7-result',image) 45 | 46 | src = cv.imread("./raw_data/4.jpg") 47 | # cv.imshow("gray_img", src) 48 | cv.namedWindow("result", cv.WINDOW_NORMAL) 49 | water_shed(src) 50 | cv.waitKey(0) 51 | cv.destroyAllWindows() -------------------------------------------------------------------------------- /problems.docx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/LelandYan/Image_processing/cec513730432b36ff434f77364b2338a253e98c1/problems.docx -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | certifi==2019.9.11 2 | cloudpickle==1.2.2 3 | cycler==0.10.0 4 | cytoolz==0.10.0 5 | dask==2.6.0 6 | decorator==4.4.0 7 | imageio==2.6.0 8 | kiwisolver==1.1.0 9 | matplotlib==3.1.1 10 | mkl-fft==1.0.14 11 | mkl-random==1.1.0 12 | mkl-service==2.3.0 13 | networkx==2.3 14 | numpy==1.17.3 15 | olefile==0.46 16 | opencv-contrib-python==3.4.2.16 17 | opencv-python==3.4.2.16 18 | Pillow==6.2.0 19 | pyparsing==2.4.2 20 | python-dateutil==2.8.0 21 | pytz==2019.3 22 | PyWavelets==1.0.3 23 | scikit-image==0.15.0 24 | scipy==1.3.1 25 | six==1.12.0 26 | toolz==0.10.0 27 | tornado==6.0.3 28 | wincertstore==0.2 29 | --------------------------------------------------------------------------------