Python中的人脸识别

Question

我能够找到这些面孔，并使用python将它们保存在本地目录中，然后根据下面视频中的代码打开cv

import cv2
import numpy as np
import os

vc = cv2.VideoCapture('new1.avi')
c=1

if vc.isOpened():
    rval , frame = vc.read()
else:
    rval = False

while rval:
	rval, frame = vc.read()
	cv2.imwrite(str(c) + '.jpg',frame)
	image_name=str(c)+'.jpg'
	cascPath = "haarcascade_frontalface_default.xml"
	faceCascade = cv2.CascadeClassifier(cascPath)

	image=cv2.imread(image_name)
	gray=cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)


	faces = faceCascade.detectMultiScale(
		gray,
		scaleFactor=1.2,
		minNeighbors=5,
		minSize=(30, 30),
		flags = cv2.cv.CV_HAAR_SCALE_IMAGE
	)

	print "Found {0} faces!".format(len(faces))

	if len(faces)>=1:
		for (x, y, w, h) in faces:
			cv2.rectangle(image, (x, y), (x+w, y+h), (0, 255, 0), 2)
		cv2.imshow("Faces found" ,image)
		cv2.waitKey(0)
		
		
	else:
		a="rm "+image_name
		os.popen(a)

	c = c + 1
	cv2.waitKey(1)
        
vc.release()

但是现在我想知道那个视频里有脸的人的身份......

我如何定义此人的身份？

喜欢扫描人脸并将其匹配到本地人脸数据库中，如果找到匹配项，请给出姓名等

Answer 1

您可以使用特征脸识别器、FisherFaceRecognizer或LBHP

这三种算法都内置于python中

# Create a recognizer object  
recognizer = cv2.face.createEigenFaceRecognizer()
# But Remember for EigenFaces all the images whether training or testing has to be of same shape
    #==========================================================================
    # get_images_and_labels function will give us list of images and list of labels to train our recognizer that we created in the first line
    # function requires the path of the directory where all the images is stored
    #===========================================================================
    def get_images_and_labels(path):
        # Append all the absolute image paths in a list image_paths
        image_paths = [os.path.join(path, f) for f in os.listdir(path) if not 
        f.endswith('.sad')]
        # images will contains face images
        images = []
        # labels will contains the label that is assigned to the image
        labels = []
        final_images = []
        largest_image_size = 0
        largest_width = 0
        largest_height = 0

        for image_path in image_paths:
           # Read the image and convert to grayscale
           image_pil = Image.open(image_path).convert('L')
           # Convert the image format into numpy array
           image = np.array(image_pil, 'uint8')
           # Get the label of the image
           nbr = int(os.path.split(image_path)[1].split(".")[0].replace("subject", ""))
           # Detect the face in the image
           faces = faceCascade.detectMultiScale(image)
           # If face is detected, append the face to images and the label to labels

        for (x, y, w, h) in faces:
            images.append(image[y: y + h, x: x + w])
            labels.append(nbr)
            cv2.imshow("Adding faces to traning set...", image[y: y + h, x: x + w])
            cv2.waitKey(50)
           # return the images list and labels list

        for image in images:
            if image.size > largest_image_size:
                largest_image_size = image.size
        largest_width, largest_height = image.shape

        for image in images:
            image = cv2.resize(image, (largest_width, largest_height), interpolation=cv2.INTER_CUBIC)
            final_images.append(image)

    return final_images, labels, largest_width, largest_height

#===================================================================
# Perform the tranining
# trainer takes two parameters as input
# first parameter is the list of images
# second parameter is a numpy array of their corresponding labels
#===================================================================
recognizer.train(images, np.array(labels)) # training takes as input the   list 



image_paths = [os.path.join(path, f) for f in os.listdir(path) if f.endswith('.sad')]
for image_path in image_paths:
    predict_image_pil = Image.open(image_path).convert('L')
    predict_image = np.array(predict_image_pil, 'uint8')
    faces = faceCascade.detectMultiScale(predict_image)
    for (x, y, w, h) in faces:
        result = cv2.face.MinDistancePredictCollector()
        predict_image = predict_image[y: y + h, x: x + w] 
        predict_image = cv2.resize(predict_image, (max_width, max_heigth), interpolation=cv2.INTER_CUBIC)

        # =========================================================  
        # predict method will give us the prediction
        # we will get the label in the next statement
        # predicted_image is the image that you want to recognize 
        # =========================================================  
        recognizer.predict(predict_image, result, 0) # this statement will give the prediction

        # ========================================== 
        # This statement below will give us label 
        # ========================================== 
        nbr_predicted = result.getLabel() 

        # ========================================== 
        # conf will tell us how much confident our recognizer is in it's prediction
        # ========================================== 
        conf = result.getDist()
        nbr_actual = int(os.path.split(image_path)[1].split(".")[0].replace("subject", ""))
        if nbr_actual == nbr_predicted:
           print("{} is Correctly Recognized with confidence {}".format(nbr_actual, conf))
        else:
            print("{} is Incorrect Recognized as {}".format(nbr_actual, nbr_predicted))
sys.exit()

Answer 2

区分照片中的人并不是一件小事，但也有一些例子。正如德曼在之前的评论中提到的，最好的方法是使用机器学习来教程序不同的人的脸是什么样子。一种方法是手动查找和提取人脸的特征，例如眼睛之间的距离与眼睛和嘴巴之间的距离等。不过，这需要注意镜头畸变和透视的影响。有多篇研究论文讨论了最佳技术，比如本文使用一组人脸的特征向量来寻找使用特征人脸的最可能匹配人脸识别

Python有一个机器学习工具箱，名为scikit learn，它实现了对分类、回归、聚类等的支持。你可以用它来训练神经网络和支持向量机等。下面是一个完整的示例，演示了如何使用支持向量机、scikit learn和python实现特征脸方法：使用python完成实现