自学教程：人脸识别实战之Opencv+SVM实现人脸识别

# import the necessary packagesimport numpy as npimport pickleimport cv2import osimport os

def list_images(basePath, contains=None):    # return the set of files that are valid    return list_files(basePath, validExts=image_types, contains=contains)def list_files(basePath, validExts=None, contains=None):    # loop over the directory structure    for (rootDir, dirNames, filenames) in os.walk(basePath):        # loop over the filenames in the current directory        for filename in filenames:            # if the contains string is not none and the filename does not contain            # the supplied string, then ignore the file            if contains is not None and filename.find(contains) == -1:                continue            # determine the file extension of the current file            ext = filename[filename.rfind("."):].lower()            # check to see if the file is an image and should be processed            if validExts is None or ext.endswith(validExts):                # construct the path to the image and yield it                imagePath = os.path.join(rootDir, filename)                yield imagePathdef resize(image, width=None, height=None, inter=cv2.INTER_AREA):    dim = None    (h, w) = image.shape[:2]    # 如果高和宽为None则直接返回    if width is None and height is None:        return image    # 检查宽是否是None    if width is None:        # 计算高度的比例并并按照比例计算宽度        r = height / float(h)        dim = (int(w * r), height)    # 高为None    else:        # 计算宽度比例，并计算高度        r = width / float(w)        dim = (width, int(h * r))    resized = cv2.resize(image, dim, interpolation=inter)    # return the resized image    return resized

dataset_path='dataset'embeddings_path='output/embeddings.pickle'detector_path='face_dete_model'embedding_model='nn4.small2.v1.t7'confidence_low=0.5

print("loading face detector...")protoPath = os.path.sep.join([detector_path, "deploy.proto.txt"])modelPath = os.path.sep.join([detector_path,"res10_300x300_ssd_iter_140000_fp16.caffemodel"])detector = cv2.dnn.readNetFromCaffe(protoPath, modelPath)# 加载序列化的人脸编码模型print("loading face recognizer...")embedder = cv2.dnn.readNetFromTorch(embedding_model)# 获取数据集中输入图像的路径print("quantifying faces...")imagePaths = list(list_images(dataset_path))# 初始化我们提取的面部编码列表和相应的人名knownEmbeddings = []knownNames = []# 初始化处理的人脸总数total = 0# loop over the image pathsfor (i, imagePath) in enumerate(imagePaths):    # extract the person name from the image path    print("processing image {}/{}".format(i + 1,len(imagePaths)))    name = imagePath.split(os.path.sep)[-2]    # 加载图像，将其调整为宽度为 600 像素（同时保持纵横比），然后抓取图像尺寸    image = cv2.imread(imagePath)    image = resize(image, width=600)    (h, w) = image.shape[:2]    # 从图像构建一个 blob    imageBlob = cv2.dnn.blobFromImage(        cv2.resize(image, (300, 300)), 1.0, (300, 300),        (104.0, 177.0, 123.0), swapRB=False, crop=False)    # 使用 OpenCV 的基于深度学习的人脸检测器来定位输入图像中的人脸    detector.setInput(imageBlob)    detections = detector.forward()    # ensure at least one face was found    if len(detections) > 0:        # 假设每个图像只有一张脸，所以找到概率最大的边界框        i = np.argmax(detections[0, 0, :, 2])        confidence = detections[0, 0, i, 2]        # 确保最大概率的检测也意味着我们的最小概率测试（从而帮助过滤掉弱检测）        if confidence > confidence_low:            # 计算人脸边界框的 (x, y) 坐标            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])            (startX, startY, endX, endY) = box.astype("int")            # 提取人脸ROI并抓取ROI维度            face = image[startY:endY, startX:endX]            (fH, fW) = face.shape[:2]            # 确保人脸宽度和高度足够大            if fW < 20 or fH < 20:                continue            # 为人脸 ROI 构造一个 blob，然后将 blob 通过我们的人脸嵌入模型来获得人脸的 128-d 量化            faceBlob = cv2.dnn.blobFromImage(face, 1.0 / 255,                                             (96, 96), (0, 0, 0), swapRB=True, crop=False)            embedder.setInput(faceBlob)            vec = embedder.forward()            # 将人名+对应的人脸嵌入添加到各自的列表中            knownNames.append(name)            knownEmbeddings.append(vec.flatten())            total += 1# 保存编码文件print("serializing {} encodings...".format(total))data = {"embeddings": knownEmbeddings, "names": knownNames}f = open(embeddings_path, "wb")f.write(pickle.dumps(data))f.close()