200字范文 > 人脸活体检测人脸识别：眨眼+张口

人脸活体检测人脸识别：眨眼+张口

时间：2023-07-23 02:27:36

相关推荐

人脸活体检测人脸识别：眨眼+张口

一：dlib的shape_predictor_68_face_landmarks模型

该模型能够检测人脸的68个特征点（facial landmarks），定位图像中的眼睛，眉毛，鼻子，嘴巴，下颌线（ROI，Region of Interest）

下颌线[1,17]左眼眉毛[18,22]右眼眉毛[23,27]鼻梁[28,31]鼻子[32,36]左眼[37,42]右眼[43,48]上嘴唇外边缘[49,55] 上嘴唇内边缘[66,68] 下嘴唇外边缘[56,60] 下嘴唇内边缘[61,65]

在使用的过程中对应的下标要减1，像数组的下标是从0开始。

二、眨眼检测

基本原理：计算眼睛长宽比 Eye Aspect Ratio，EAR.当人眼睁开时，EAR在某个值上下波动，当人眼闭合时，EAR迅速下降，理论上会接近于零，当时人脸检测模型还没有这么精确。所以我们认为当EAR低于某个阈值时，眼睛处于闭合状态。为检测眨眼次数，需要设置同一次眨眼的连续帧数。眨眼速度比较快，一般1~3帧就完成了眨眼动作。两个阈值都要根据实际情况设置。

程序实现：

from imutils import face_utilsimport numpy as npimport dlibimport cv2# 眼长宽比例def eye_aspect_ratio(eye):# (|e1-e5|+|e2-e4|) / (2|e0-e3|)A = np.linalg.norm(eye[1] - eye[5])B = np.linalg.norm(eye[2] - eye[4])C = np.linalg.norm(eye[0] - eye[3])ear = (A + B) / (2.0 * C)return ear# 进行活体检测（包含眨眼和张嘴）def liveness_detection():vs = cv2.VideoCapture(0) # 调用第一个摄像头的信息# 眼长宽比例值EAR_THRESH = 0.15EAR_CONSEC_FRAMES_MIN = 1EAR_CONSEC_FRAMES_MAX = 3 # 当EAR小于阈值时，接连多少帧一定发生眨眼动作# 初始化眨眼的连续帧数blink_counter = 0# 初始化眨眼次数总数blink_total = 0print("[INFO] loading facial landmark predictor...")# 人脸检测器detector = dlib.get_frontal_face_detector()# 特征点检测器predictor = dlib.shape_predictor("model/shape_predictor_68_face_landmarks.dat")# 获取左眼的特征点(lStart, lEnd) = face_utils.FACIAL_LANDMARKS_IDXS["left_eye"]# 获取右眼的特征点(rStart, rEnd) = face_utils.FACIAL_LANDMARKS_IDXS["right_eye"]print("[INFO] starting video stream thread...")while True:flag, frame = vs.read() # 返回一帧的数据if not flag:print("不支持摄像头", flag)breakif frame is not None:gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) # 转成灰度图像rects = detector(gray, 0) # 人脸检测# 只能处理一张人脸if len(rects) == 1:shape = predictor(gray, rects[0]) # 保存68个特征点坐标的<class 'dlib.dlib.full_object_detection'>对象shape = face_utils.shape_to_np(shape) # 将shape转换为numpy数组，数组中每个元素为特征点坐标left_eye = shape[lStart:lEnd] # 取出左眼对应的特征点right_eye = shape[rStart:rEnd] # 取出右眼对应的特征点left_ear = eye_aspect_ratio(left_eye) # 计算左眼EARright_ear = eye_aspect_ratio(right_eye) # 计算右眼EARear = (left_ear + right_ear) / 2.0 # 求左右眼EAR的均值left_eye_hull = cv2.convexHull(left_eye) # 寻找左眼轮廓right_eye_hull = cv2.convexHull(right_eye) # 寻找右眼轮廓# mouth_hull = cv2.convexHull(mouth) # 寻找嘴巴轮廓cv2.drawContours(frame, [left_eye_hull], -1, (0, 255, 0), 1) # 绘制左眼轮廓cv2.drawContours(frame, [right_eye_hull], -1, (0, 255, 0), 1) # 绘制右眼轮廓# EAR低于阈值，有可能发生眨眼，眨眼连续帧数加一次if ear < EAR_THRESH:blink_counter += 1# EAR高于阈值，判断前面连续闭眼帧数，如果在合理范围内，说明发生眨眼else:if EAR_CONSEC_FRAMES_MIN <= blink_counter <= EAR_CONSEC_FRAMES_MAX:blink_total += 1blink_counter = 0cv2.putText(frame, "Blinks: {}".format(blink_total), (0, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)cv2.putText(frame, "EAR: {:.2f}".format(ear), (300, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)elif len(rects) == 0:cv2.putText(frame, "No face!", (0, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)else:cv2.putText(frame, "More than one face!", (0, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)cv2.namedWindow("Frame", cv2.WINDOW_NORMAL)cv2.imshow("Frame", frame)# 按下q键退出循环（鼠标要点击一下图片使图片获得焦点）if cv2.waitKey(1) & 0xFF == ord('q'):breakcv2.destroyAllWindows()vs.release()liveness_detection()

三、张口检测

检测原理：类似眨眼检测，计算Mouth Aspect Ratio,MAR.当MAR大于设定的阈值时，认为张开了嘴巴。

1：采用的判定是张开后闭合计算一次张嘴动作。

mar # 嘴长宽比例

MAR_THRESH = 0.2 # 嘴长宽比例值

mouth_status_open # 初始化张嘴状态为闭嘴

当mar大于设定的比例值表示张开，张开后闭合代表一次张嘴动作

# 通过张、闭来判断一次张嘴动作if mar > MAR_THRESH:mouth_status_open = 1else:if mouth_status_open:mouth_total += 1mouth_status_open = 0

2：嘴长宽比例的计算

# 嘴长宽比例def mouth_aspect_ratio(mouth):A = np.linalg.norm(mouth[1] - mouth[7]) # 61, 67B = np.linalg.norm(mouth[3] - mouth[5]) # 63, 65C = np.linalg.norm(mouth[0] - mouth[4]) # 60, 64mar = (A + B) / (2.0 * C)return mar

原本采用嘴唇外边缘来计算，发现嘟嘴也会被判定为张嘴，故才用嘴唇内边缘进行计算，会更加准确。

这里mouth下标的值取决于取的是“mouth”还是“inner_mouth”，由于我要画的轮廓是内嘴，所以我采用的是inner_mouth

(mStart, mEnd) = face_utils.FACIAL_LANDMARKS_IDXS["inner_mouth"]

打开以下方法，进入到源码，可以看到每个特征点对应的下标是不一样的，对应的mouth特征点的下标也是不同的

（以上的区间包左边代表开始下标，右边值-1）从上面可知mouth是从（48,68），inner_mouth从(60, 68)，mouth包含inner_mouth,如果取得是mouth的值，则嘴长宽比例的计算如下

# 嘴长宽比例def mouth_aspect_ratio(mouth):# (|m13-m19|+|m15-m17|)/(2|m12-m16|)A = np.linalg.norm(mouth[13] - mouth[19]) # 61, 67B = np.linalg.norm(mouth[15] - mouth[17]) # 63, 65C = np.linalg.norm(mouth[12] - mouth[16]) # 60, 64mar = (A + B) / (2.0 * C)return mar

3：完整程序实现如下

from imutils import face_utilsimport numpy as npimport dlibimport cv2# 嘴长宽比例def mouth_aspect_ratio(mouth):A = np.linalg.norm(mouth[1] - mouth[7]) # 61, 67B = np.linalg.norm(mouth[3] - mouth[5]) # 63, 65C = np.linalg.norm(mouth[0] - mouth[4]) # 60, 64mar = (A + B) / (2.0 * C)return mar# 进行活体检测（张嘴）def liveness_detection():vs = cv2.VideoCapture(0) # 调用第一个摄像头的信息# 嘴长宽比例值MAR_THRESH = 0.2# 初始化张嘴次数mouth_total = 0# 初始化张嘴状态为闭嘴mouth_status_open = 0print("[INFO] loading facial landmark predictor...")# 人脸检测器detector = dlib.get_frontal_face_detector()# 特征点检测器predictor = dlib.shape_predictor("model/shape_predictor_68_face_landmarks.dat")# 获取嘴巴特征点(mStart, mEnd) = face_utils.FACIAL_LANDMARKS_IDXS["inner_mouth"]print("[INFO] starting video stream thread...")while True:flag, frame = vs.read() # 返回一帧的数据if not flag:print("不支持摄像头", flag)breakif frame is not None:# 图片转换成灰色（去除色彩干扰，让图片识别更准确）gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)rects = detector(gray, 0) # 人脸检测# 只能处理一张人脸if len(rects) == 1:shape = predictor(gray, rects[0]) # 保存68个特征点坐标的<class 'dlib.dlib.full_object_detection'>对象shape = face_utils.shape_to_np(shape) # 将shape转换为numpy数组，数组中每个元素为特征点坐标inner_mouth = shape[mStart:mEnd] # 取出嘴巴对应的特征点mar = mouth_aspect_ratio(inner_mouth) # 求嘴巴mar的均值mouth_hull = cv2.convexHull(inner_mouth) # 寻找内嘴巴轮廓cv2.drawContours(frame, [mouth_hull], -1, (0, 255, 0), 1) # 绘制嘴巴轮廓# 通过张、闭来判断一次张嘴动作if mar > MAR_THRESH:mouth_status_open = 1else:if mouth_status_open:mouth_total += 1mouth_status_open = 0cv2.putText(frame, "Mouth: {}".format(mouth_total),(130, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)cv2.putText(frame, "MAR: {:.2f}".format(mar), (450, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)elif len(rects) == 0:cv2.putText(frame, "No face!", (0, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)else:cv2.putText(frame, "More than one face!", (0, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)cv2.namedWindow("Frame", cv2.WINDOW_NORMAL)cv2.imshow("Frame", frame)# 按下q键退出循环（鼠标要点击一下图片使图片获得焦点）if cv2.waitKey(1) & 0xFF == ord('q'):breakcv2.destroyAllWindows()vs.release()liveness_detection()

三：眨眼和张嘴结合（摄像头）

from imutils import face_utilsimport numpy as npimport dlibimport cv2# 眼长宽比例def eye_aspect_ratio(eye):# (|e1-e5|+|e2-e4|) / (2|e0-e3|)A = np.linalg.norm(eye[1] - eye[5])B = np.linalg.norm(eye[2] - eye[4])C = np.linalg.norm(eye[0] - eye[3])ear = (A + B) / (2.0 * C)return ear# 嘴长宽比例def mouth_aspect_ratio(mouth):A = np.linalg.norm(mouth[1] - mouth[7]) # 61, 67B = np.linalg.norm(mouth[3] - mouth[5]) # 63, 65C = np.linalg.norm(mouth[0] - mouth[4]) # 60, 64mar = (A + B) / (2.0 * C)return mar# 进行活体检测（包含眨眼和张嘴）def liveness_detection():vs = cv2.VideoCapture(0) # 调用第一个摄像头的信息# 眼长宽比例值EAR_THRESH = 0.15EAR_CONSEC_FRAMES_MIN = 1EAR_CONSEC_FRAMES_MAX = 5 # 当EAR小于阈值时，接连多少帧一定发生眨眼动作# 嘴长宽比例值MAR_THRESH = 0.2# 初始化眨眼的连续帧数blink_counter = 0# 初始化眨眼次数总数blink_total = 0# 初始化张嘴次数mouth_total = 0# 初始化张嘴状态为闭嘴mouth_status_open = 0print("[INFO] loading facial landmark predictor...")# 人脸检测器detector = dlib.get_frontal_face_detector()# 特征点检测器predictor = dlib.shape_predictor("model/shape_predictor_68_face_landmarks.dat")# 获取左眼的特征点(lStart, lEnd) = face_utils.FACIAL_LANDMARKS_IDXS["left_eye"]# 获取右眼的特征点(rStart, rEnd) = face_utils.FACIAL_LANDMARKS_IDXS["right_eye"]# 获取嘴巴特征点(mStart, mEnd) = face_utils.FACIAL_LANDMARKS_IDXS["inner_mouth"]print("[INFO] starting video stream thread...")while True:flag, frame = vs.read() # 返回一帧的数据if not flag:print("不支持摄像头", flag)breakif frame is not None:# 图片转换成灰色（去除色彩干扰，让图片识别更准确）gray = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)rects = detector(gray, 0) # 人脸检测# 只能处理一张人脸if len(rects) == 1:shape = predictor(gray, rects[0]) # 保存68个特征点坐标的<class 'dlib.dlib.full_object_detection'>对象shape = face_utils.shape_to_np(shape) # 将shape转换为numpy数组，数组中每个元素为特征点坐标left_eye = shape[lStart:lEnd] # 取出左眼对应的特征点right_eye = shape[rStart:rEnd] # 取出右眼对应的特征点left_ear = eye_aspect_ratio(left_eye) # 计算左眼EARright_ear = eye_aspect_ratio(right_eye) # 计算右眼EARear = (left_ear + right_ear) / 2.0 # 求左右眼EAR的均值inner_mouth = shape[mStart:mEnd] # 取出嘴巴对应的特征点mar = mouth_aspect_ratio(inner_mouth) # 求嘴巴mar的均值left_eye_hull = cv2.convexHull(left_eye) # 寻找左眼轮廓right_eye_hull = cv2.convexHull(right_eye) # 寻找右眼轮廓mouth_hull = cv2.convexHull(inner_mouth) # 寻找内嘴巴轮廓cv2.drawContours(frame, [left_eye_hull], -1, (0, 255, 0), 1) # 绘制左眼轮廓cv2.drawContours(frame, [right_eye_hull], -1, (0, 255, 0), 1) # 绘制右眼轮廓cv2.drawContours(frame, [mouth_hull], -1, (0, 255, 0), 1) # 绘制嘴巴轮廓# EAR低于阈值，有可能发生眨眼，眨眼连续帧数加一次if ear < EAR_THRESH:blink_counter += 1# EAR高于阈值，判断前面连续闭眼帧数，如果在合理范围内，说明发生眨眼else:# if the eyes were closed for a sufficient number of# then increment the total number of blinksif EAR_CONSEC_FRAMES_MIN <= blink_counter <= EAR_CONSEC_FRAMES_MAX:blink_total += 1blink_counter = 0# 通过张、闭来判断一次张嘴动作if mar > MAR_THRESH:mouth_status_open = 1else:if mouth_status_open:mouth_total += 1mouth_status_open = 0cv2.putText(frame, "Blinks: {}".format(blink_total), (0, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)cv2.putText(frame, "Mouth: {}".format(mouth_total),(130, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)cv2.putText(frame, "EAR: {:.2f}".format(ear), (300, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)cv2.putText(frame, "MAR: {:.2f}".format(mar), (450, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)elif len(rects) == 0:cv2.putText(frame, "No face!", (0, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)else:cv2.putText(frame, "More than one face!", (0, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)cv2.namedWindow("Frame", cv2.WINDOW_NORMAL)cv2.imshow("Frame", frame)# 按下q键退出循环（鼠标要点击一下图片使图片获得焦点）if cv2.waitKey(1) & 0xFF == ord('q'):breakcv2.destroyAllWindows()vs.release()# 调用摄像头进行张嘴眨眼活体检测liveness_detection()

四：采用视频进行活体检测

最大的区别是原来通过摄像头获取一帧一帧的视频流进行判断，现在是通过视频获取一帧一帧的视频流进行判断

1：先看下获取摄像头的图像信息

# -*-coding:GBK -*-import cv2from PIL import Image, ImageDrawimport numpy as np# 1.调用摄像头# 2.读取摄像头图像信息# 3.在图像上添加文字信息# 4.保存图像cap = cv2.VideoCapture(0) # 调用第一个摄像头信息while True:flag, frame = cap.read() # 返回一帧的数据# #返回值：flag：bool值：True：读取到图片，False：没有读取到图片 frame：一帧的图片# BGR是cv2 的图像保存格式，RGB是PIL的图像保存格式，在转换时需要做格式上的转换img_PIL = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))draw = ImageDraw.Draw(img_PIL)draw.text((100, 100), 'press q to exit', fill=(255, 255, 255))# 将frame对象转换成cv2的格式frame = cv2.cvtColor(np.array(img_PIL), cv2.COLOR_RGB2BGR)cv2.imshow('capture', frame)if cv2.waitKey(1) & 0xFF == ord('q'):cv2.imwrite('images/out.jpg', frame)breakcap.release()

2：获取视频的图像信息

# -*-coding:GBK -*-import cv2from PIL import Image, ImageDrawimport numpy as np# 1.调用摄像头# 2.读取摄像头图像信息# 3.在图像上添加文字信息# 4.保存图像cap = cv2.VideoCapture(r'video\face13.mp4') # 调用第一个摄像头信息while True:flag, frame = cap.read() # 返回一帧的数据if not flag:breakif frame is not None:# BGR是cv2 的图像保存格式，RGB是PIL的图像保存格式，在转换时需要做格式上的转换img_PIL = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))draw = ImageDraw.Draw(img_PIL)draw.text((100, 100), 'press q to exit', fill=(255, 255, 255))# # 将frame对象转换成cv2的格式frame = cv2.cvtColor(np.array(img_PIL), cv2.COLOR_RGB2BGR)cv2.imshow('capture', frame)if cv2.waitKey(1) & 0xFF == ord('q'):cv2.imwrite('images/out.jpg', frame)breakcv2.destroyAllWindows()cap.release()

五：视频进行人脸识别和活体检测

1：原理

计算当出现1次眨眼或1次张嘴就判断为活人，记录下一帧的人脸图片，和要判定的人员图片进行比对，获取比对后的相似度，进行判断是否是同一个人，为了增加判断的速度，才用2帧进行一次活体检测判断。

2：代码实现

import face_recognitionfrom imutils import face_utilsimport numpy as npimport dlibimport cv2import sys# 初始化眨眼次数blink_total = 0# 初始化张嘴次数mouth_total = 0# 设置图片存储路径pic_path = r'images\viode_face.jpg'# 图片数量pic_total = 0# 初始化眨眼的连续帧数以及总的眨眼次数blink_counter = 0# 初始化张嘴状态为闭嘴mouth_status_open = 0def getFaceEncoding(src):image = face_recognition.load_image_file(src) # 加载人脸图片# 获取图片人脸定位[(top,right,bottom,left )]face_locations = face_recognition.face_locations(image)img_ = image[face_locations[0][0]:face_locations[0][2], face_locations[0][3]:face_locations[0][1]]img_ = cv2.cvtColor(img_, cv2.COLOR_BGR2RGB)# display(img_)face_encoding = face_recognition.face_encodings(image, face_locations)[0] # 对人脸图片进行编码return face_encodingdef simcos(a, b):a = np.array(a)b = np.array(b)dist = np.linalg.norm(a - b) # 二范数sim = 1.0 / (1.0 + dist) #return sim# 提供对外比对的接口返回比对的相似度def comparison(face_src1, face_src2):xl1 = getFaceEncoding(face_src1)xl2 = getFaceEncoding(face_src2)value = simcos(xl1, xl2)print(value)# 眼长宽比例def eye_aspect_ratio(eye):# (|e1-e5|+|e2-e4|) / (2|e0-e3|)A = np.linalg.norm(eye[1] - eye[5])B = np.linalg.norm(eye[2] - eye[4])C = np.linalg.norm(eye[0] - eye[3])ear = (A + B) / (2.0 * C)return ear# 嘴长宽比例def mouth_aspect_ratio(mouth):A = np.linalg.norm(mouth[1] - mouth[7]) # 61, 67B = np.linalg.norm(mouth[3] - mouth[5]) # 63, 65C = np.linalg.norm(mouth[0] - mouth[4]) # 60, 64mar = (A + B) / (2.0 * C)return mar# 进行活体检测（包含眨眼和张嘴）# filePath 视频路径def liveness_detection():global blink_total # 使用global声明blink_total，在函数中就可以修改全局变量的值global mouth_totalglobal pic_totalglobal blink_counterglobal mouth_status_open# 眼长宽比例值EAR_THRESH = 0.15EAR_CONSEC_FRAMES_MIN = 1EAR_CONSEC_FRAMES_MAX = 5 # 当EAR小于阈值时，接连多少帧一定发生眨眼动作# 嘴长宽比例值MAR_THRESH = 0.2# 人脸检测器detector = dlib.get_frontal_face_detector()# 特征点检测器predictor = dlib.shape_predictor("model/shape_predictor_68_face_landmarks.dat")# 获取左眼的特征点(lStart, lEnd) = face_utils.FACIAL_LANDMARKS_IDXS["left_eye"]# 获取右眼的特征点(rStart, rEnd) = face_utils.FACIAL_LANDMARKS_IDXS["right_eye"]# 获取嘴巴特征点(mStart, mEnd) = face_utils.FACIAL_LANDMARKS_IDXS["inner_mouth"]vs = cv2.VideoCapture(video_path)# 总帧数(frames)frames = vs.get(cv2.CAP_PROP_FRAME_COUNT)frames_total = int(frames)for i in range(frames_total):ok, frame = vs.read(i) # 读取视频流的一帧if not ok:breakif frame is not None and i % 2 == 0:# 图片转换成灰色（去除色彩干扰，让图片识别更准确）gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)rects = detector(gray, 0) # 人脸检测# 只能处理一张人脸if len(rects) == 1:if pic_total == 0:cv2.imwrite(pic_path, frame) # 存储为图像,保存名为文件夹名_数字（第几个文件）.jpgcv2.waitKey(1)pic_total += 1shape = predictor(gray, rects[0]) # 保存68个特征点坐标的<class 'dlib.dlib.full_object_detection'>对象shape = face_utils.shape_to_np(shape) # 将shape转换为numpy数组，数组中每个元素为特征点坐标left_eye = shape[lStart:lEnd] # 取出左眼对应的特征点right_eye = shape[rStart:rEnd] # 取出右眼对应的特征点left_ear = eye_aspect_ratio(left_eye) # 计算左眼EARright_ear = eye_aspect_ratio(right_eye) # 计算右眼EARear = (left_ear + right_ear) / 2.0 # 求左右眼EAR的均值mouth = shape[mStart:mEnd] # 取出嘴巴对应的特征点mar = mouth_aspect_ratio(mouth) # 求嘴巴mar的均值# EAR低于阈值，有可能发生眨眼，眨眼连续帧数加一次if ear < EAR_THRESH:blink_counter += 1# EAR高于阈值，判断前面连续闭眼帧数，如果在合理范围内，说明发生眨眼else:if EAR_CONSEC_FRAMES_MIN <= blink_counter <= EAR_CONSEC_FRAMES_MAX:blink_total += 1blink_counter = 0# 通过张、闭来判断一次张嘴动作if mar > MAR_THRESH:mouth_status_open = 1else:if mouth_status_open:mouth_total += 1mouth_status_open = 0elif len(rects) == 0 and i == 90:print("No face!")breakelif len(rects) > 1:print("More than one face!")# 判断眨眼次数大于2、张嘴次数大于1则为活体,退出循环if blink_total >= 1 or mouth_total >= 1:breakcv2.destroyAllWindows()vs.release()# video_path, src = sys.argv[1], sys.argv[2]video_path = r'video\face13.mp4'# 输入的video文件夹位置# src = r'C:\Users\666\Desktop\zz5.jpg'liveness_detection()print("眨眼次数》》", blink_total)print("张嘴次数》》", mouth_total)# comparison(pic_path, src)