├── Face_Recog.py
└── Face_Trainer.py


/Face_Recog.py:
--------------------------------------------------------------------------------
 1 | #Program to Detect the Face and Recognise the Person based on the data from face-trainner.yml
 2 | 
 3 | import cv2 #For Image processing 
 4 | import numpy as np #For converting Images to Numerical array 
 5 | import os #To handle directories 
 6 | from PIL import Image #Pillow lib for handling images 
 7 | 
 8 | labels = ["apurva", "Elon Musk"] 
 9 | 
10 | face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
11 | recognizer = cv2.face.createLBPHFaceRecognizer()
12 | recognizer.load("face-trainner.yml")
13 | 
14 | cap = cv2.VideoCapture(0) #Get vidoe feed from the Camera
15 | 
16 | while(True):
17 | 
18 |     ret, img = cap.read() # Break video into frames 
19 |     gray  = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) #convert Video frame to Greyscale
20 |     faces = face_cascade.detectMultiScale(gray, scaleFactor=1.5, minNeighbors=5) #Recog. faces
21 |     for (x, y, w, h) in faces:
22 |     	roi_gray = gray[y:y+h, x:x+w] #Convert Face to greyscale 
23 | 
24 |     	id_, conf = recognizer.predict(roi_gray) #recognize the Face
25 |     
26 |     	if conf>=80:
27 |     		font = cv2.FONT_HERSHEY_SIMPLEX #Font style for the name 
28 |     		name = labels[id_] #Get the name from the List using ID number 
29 |     		cv2.putText(img, name, (x,y), font, 1, (0,0,255), 2)
30 |     	
31 |     	cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),2)
32 | 
33 |     cv2.imshow('Preview',img) #Display the Video
34 |     if cv2.waitKey(20) & 0xFF == ord('q'):
35 |     	break
36 | 
37 | # When everything done, release the capture
38 | cap.release()
39 | cv2.destroyAllWindows()
40 | 


--------------------------------------------------------------------------------
/Face_Trainer.py:
--------------------------------------------------------------------------------
 1 | #Program to train with the faces and create a YAML file
 2 | 
 3 | import cv2 #For Image processing 
 4 | import numpy as np #For converting Images to Numerical array 
 5 | import os #To handle directories 
 6 | from PIL import Image #Pillow lib for handling images
 7 | 
 8 | face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
 9 | recognizer = cv2.face.createLBPHFaceRecognizer()
10 | 
11 | Face_ID = -1 
12 | pev_person_name = ""
13 | y_ID = []
14 | x_train = []
15 | 
16 | Face_Images = os.path.join(os.getcwd(), "Face_Images") #Tell the program where we have saved the face images 
17 | print (Face_Images)
18 | 
19 | for root, dirs, files in os.walk(Face_Images): #go to the face image directory 
20 |     for file in files: #check every directory in it 
21 |             if file.endswith("jpeg") or file.endswith("jpg") or file.endswith("png"): #for image files ending with jpeg,jpg or png 
22 | 			path = os.path.join(root, file)
23 | 			person_name = os.path.basename(root)
24 | 			print(path, person_name)
25 | 
26 | 			
27 | 			if pev_person_name!=person_name: #Check if the name of person has changed 
28 | 				Face_ID=Face_ID+1 #If yes increment the ID count 
29 | 				pev_person_name = person_name
30 | 
31 | 			
32 | 			Gery_Image = Image.open(path).convert("L") # convert the image to greysclae using Pillow
33 | 			Crop_Image = Gery_Image.resize( (800,800) , Image.ANTIALIAS) #Crop the Grey Image to 550*550 (Make sure your face is in the center in all image)
34 | 			Final_Image = np.array(Crop_Image, "uint8")
35 | 			#print(Numpy_Image)
36 | 			faces = face_cascade.detectMultiScale(Final_Image, scaleFactor=1.5, minNeighbors=5) #Detect The face in all sample image 
37 | 			print (Face_ID,faces)
38 | 
39 | 			for (x,y,w,h) in faces:
40 | 				roi = Final_Image[y:y+h, x:x+w] #crop the Region of Interest (ROI)
41 | 				x_train.append(roi)
42 | 				y_ID.append(Face_ID)
43 | 
44 | recognizer.train(x_train, np.array(y_ID)) #Create a Matrix of Training data 
45 | recognizer.save("face-trainner.yml") #Save the matrix as YML file 
46 | 


--------------------------------------------------------------------------------