因为某些原因需要眨眼识别，看到这个第一个想到的就是python，但是没接触过这个语言，所以我先看的java的写法，发现挺少。于是开始下载python开始了下载各种软件的道路。。。

原网址

虽然开始是在CSDN上花45积分下载的，但是发现这只是国外大佬写的。在这里给出国外大佬的原网址，就不给CSDN的了（明明人家免费，还在CSDN上卖45积分(小声BB)）。

//04/24/eye-blink-detection-opencv-python-dlib/

问题

原网址上相关配置已经很详细了。在这里我就写我自己碰到的坑。。。

主要是这些opencv，numpy,以及dlib库，scipy库。

除了dlib库其他都是直接按照网上教程直接成功的。

在这就说一下这个安装吧，找了无数的方法。最后成功了，而且还是个超级简单的。。。

首先下载dlib-19.17.0-cp37-cp37m-win_amd64.whl我已经把这个文件放在了蓝奏云。

然后直接安装，在解压好的文件夹的cmd窗口输入下面的就可以了。

pip install 文件名.whl

这里就不配安装好的图了。

wink.py的代码贴出来(原文并没有中文，中文是我机翻的)

# Command line parameters# python Wink.py --shape-predictor shape_predictor_68_face_landmarks.dat --video your videoname.mp4# python Wink.py --shape-predictor shape_predictor_68_face_landmarks.dat# import the necessary packagesfrom scipy.spatial import distance as distfrom imutils.video import FileVideoStreamfrom imutils.video import VideoStreamfrom imutils import face_utilsimport numpy as npimport argparseimport imutilsimport timeimport dlibimport cv2import winsounddef eye_aspect_ratio(eye):# compute the euclidean distances between the two sets of vertical eye landmarks (x, y)-coordinates# 计算两组垂直眼界标（x，y）坐标之间的欧几里得距离A = dist.euclidean(eye[1], eye[5])B = dist.euclidean(eye[2], eye[4])# compute the euclidean distance between the horizontal eye landmark (x, y)-coordinates# 计算水平眼界标（x，y）坐标之间的欧几里得距离C = dist.euclidean(eye[0], eye[3])# compute the eye aspect ratio 计算眼睛长宽比ear = (A + B) / (2.0 * C)# return the eye aspect ratio 返回眼睛长宽比return ear# construct the argument parse and parse the arguments 构造参数解析并解析参数ap = argparse.ArgumentParser()ap.add_argument("-p", "--shape-predictor", required=True,help="path to facial landmark predictor")ap.add_argument("-v", "--video", type=str, default="",help="path to input video file")args = vars(ap.parse_args())# define two constants, one for the eye aspect ratio to indicate# blink and then a second constant for the number of consecutive frames the eye must be below the threshold# 定义两个常数，一个常数表示眼睛的纵横比以指示眨眼，然后定义第二个常数表示眼睛的连续帧数必须低于阈值EYE_AR_THRESH = 0.25EYE_AR_CONSEC_FRAMES = 2# initialize the frame counters and the total number of blinks 初始化帧计数器和闪烁总数COUNTER = 0TOTAL = 0# initialize dlib's face detector (HOG-based) and then create the facial landmark predictor# 初始化dlib的面部检测器（基于HOG），然后创建面部界标预测器print("[INFO] loading facial landmark predictor...")detector = dlib.get_frontal_face_detector()predictor = dlib.shape_predictor(args["shape_predictor"])# grab the indexes of the facial landmarks for the left and right eye, respectively# 分别获取左眼和右眼的面部标志的索引(lStart, lEnd) = face_utils.FACIAL_LANDMARKS_IDXS["left_eye"](rStart, rEnd) = face_utils.FACIAL_LANDMARKS_IDXS["right_eye"]# start the video stream thread 启动视频流线程print("[INFO] starting video stream thread...")# vs = FileVideoStream(args["video"]).start()fileStream = Truevs = VideoStream(src=0).start()fileStream = Falsetime.sleep(1.0)# loop over frames from the video stream 循环播放视频流中的帧while True:# if this is a file video stream, then we need to check if there any more frames left in the buffer to process# 如果这是文件视频流，那么我们需要检查缓冲区中是否还有剩余的帧要处理if fileStream and not vs.more():break# grab the frame from the threaded video file stream, resize it, and convert it# to grayscale channels)# 从线程视频文件流中抓取帧，调整其大小，然后将其转换为灰度通道）frame = vs.read()frame = imutils.resize(frame, width=450)gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)# detect faces in the grayscale frame 在灰度框中检测人脸rects = detector(gray, 0)# loop over the face detections 循环人脸检测for rect in rects:# determine the facial landmarks for the face region, then convert# the facial landmark (x, y)-coordinates to a NumPy array# 确定面部区域的面部界标，然后将面部界标（x，y）坐标转换为NumPy数组shape = predictor(gray, rect)shape = face_utils.shape_to_np(shape)# extract the left and right eye coordinates, then use the coordinates to compute the eye aspect ratio for both eyes# 提取左眼和右眼坐标，然后使用坐标计算两只眼睛的眼睛纵横比leftEye = shape[lStart:lEnd]rightEye = shape[rStart:rEnd]leftEAR = eye_aspect_ratio(leftEye)rightEAR = eye_aspect_ratio(rightEye)# average the eye aspect ratio together for both eyes 将两只眼睛的眼睛纵横比平均在一起ear = (leftEAR + rightEAR) / 2.0# compute the convex hull for the left and right eye, then visualize each of the eyes# 计算左眼和右眼的凸包，然后可视化每只眼睛leftEyeHull = cv2.convexHull(leftEye)rightEyeHull = cv2.convexHull(rightEye)cv2.drawContours(frame, [leftEyeHull], -1, (0, 255, 0), 1)cv2.drawContours(frame, [rightEyeHull], -1, (0, 255, 0), 1)# check to see if the eye aspect ratio is below the blink threshold, and if so, increment the blink frame counter# 检查眼睛宽高比是否低于眨眼阈值，如果是，则增加眨眼帧计数器if ear < EYE_AR_THRESH:COUNTER += 1# otherwise, the eye aspect ratio is not below the blink threshold# 否则，眼睛纵横比不低于眨眼阈值else:# if the eyes were closed for a sufficient number of then increment the total number of blinks# 如果闭上眼睛的次数足够多，则增加眨眼的总数if COUNTER >= EYE_AR_CONSEC_FRAMES:TOTAL += 1# reset the eye frame counter 重置眼框计数器COUNTER = 0# draw the total number of blinks on the frame along with the computed eye aspect ratio for the frame# 绘制帧上眨眼的总数以及计算出的帧的眼睛纵横比cv2.putText(frame, "Blinks: {}".format(TOTAL), (10, 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, "COUNTER: {}".format(COUNTER), (140, 30),cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)# show the frame show the framecv2.imshow("Frame", frame)key = cv2.waitKey(1) & 0xFF# if the `q` key was pressed, break from the loopif key == ord("q"):break# do a bit of cleanupcv2.destroyAllWindows()vs.stop()

使用

python Wink.py --shape-predictor shape_predictor_68_face_landmarks.dat --video your videoname.mp4python Wink.py --shape-predictor shape_predictor_68_face_landmarks.dat

效果图

这个可以检测摄像头也可以检测视频里的，我都试过了可以，下面来个视频（周董的说好不哭的MV）的效果图（滑稽图）。

文章原网址：

使用OpenCV，Python和dlib进行眨眼检测