《计算机视觉》—— 表情识别

• 基于 dilib 库的人脸检测
  • https://blog.csdn.net/weixin_73504499/article/details/142977202?spm=1001.2014.3001.5501
• 基于 dlib 库的人脸关键点定位
  • https://blog.csdn.net/weixin_73504499/article/details/142990867?spm=1001.2014.3001.5501

import numpy as np
import dlib
import cv2
from sklearn.metrics.pairwise import euclidean_distances
from PIL import Image, ImageDraw, ImageFont# 计算眼睛的宽高比
def eye_aspect_ratio(eye):A = euclidean_distances(eye[1].reshape(1, 2), eye[5].reshape(1, 2))B = euclidean_distances(eye[2].reshape(1, 2), eye[4].reshape(1, 2))C = euclidean_distances(eye[0].reshape(1, 2), eye[3].reshape(1, 2))ear = ((A + B) / 2.0) / Creturn ear# 计算嘴的宽高比
def MAR(shape):x = shape[50]y = shape[50].reshape(1, 2)A = euclidean_distances(shape[50].reshape(1, 2), shape[58].reshape(1, 2))B = euclidean_distances(shape[51].reshape(1, 2), shape[57].reshape(1, 2))C = euclidean_distances(shape[52].reshape(1, 2), shape[56].reshape(1, 2))D = euclidean_distances(shape[48].reshape(1, 2), shape[54].reshape(1, 2))return ((A + B + C) / 3) / D# 计算嘴宽度与脸颊宽度的比值
def MJR(shape):M = euclidean_distances(shape[48].reshape(1, 2), shape[54].reshape(1, 2))  # 嘴宽度J = euclidean_distances(shape[3].reshape(1, 2), shape[13].reshape(1, 2))  # 下颌的宽度return M / J""" 向图片中添加中文 """
def cv2AddChineseText(img, text, position, textColor=(0, 255, 0), textSize=30):if (isinstance(img, np.ndarray)):  # 判断是否是OpenCV图片类型img = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))  # 实现 array 到 image 的转换draw = ImageDraw.Draw(img)  # 在img图片上创建一个绘图的对象# 字体的格式                       C 盘中的 Windows/Fonts 中，复制到此文件夹下可看到文件名fontStyle = ImageFont.truetype("simsun.ttc", textSize, encoding="utf-8")draw.text(position, text, textColor, font=fontStyle)  # 绘制文本return cv2.cvtColor(np.asarray(img), cv2.COLOR_RGB2BGR)  # 转换回 OpenCV 格式# 构建脸部位置检测器
detector = dlib.get_frontal_face_detector()# 读取人脸关键点定位模型
predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")# 打开摄像头或视频
cap = cv2.VideoCapture(0)while True:ret, frame = cap.read()frame = cv2.flip(frame, 1)faces = detector(frame, 0)  # 获取图片中全部人脸位置for face in faces:shape = predictor(frame, face)  # 获取关键点# 将关键点转换为坐标(x,y)的形式shape = np.array([[p.x, p.y] for p in shape.parts()])# 计算嘴部的高宽比mar = MAR(shape)# 计算 “最宽/脸颊宽”mjr = MJR(shape)rightEye = shape[36:42]  # 右眼，关键点索引从36到41(不包含42)leftEye = shape[42:48]  # 左眼，关键点索引从42到47(不包含48)rightEAR = eye_aspect_ratio(rightEye)  # 计算右眼纵横比leftEAR = eye_aspect_ratio(leftEye)  # 计算左眼纵横比ear = (rightEAR + leftEAR) / 2.0  # 均值处理result = "正常"  # 默认是正常表情# 打印出实际值，可以根据该值更改阈值print("mar", mar, "\tmjr", mjr, "\tear", ear)if mar > 0.5 and ear < 0.28:result = "大笑"elif mar > 0.5 and ear > 0.28:result = "愤怒"elif mjr > 0.45:result = "微笑"# 输出中文# frame = cv2AddChineseText(frame, result, (50, 100))# cv2.putText()#输出英文mouthHull = cv2.convexHull(shape[48:61])  # 嘴型构造凸包frame = cv2AddChineseText(frame, result, mouthHull[0, 0])  # 多人脸cv2.drawContours(frame, [mouthHull], -1, (0, 255, 0), 1)  # 画出凸包cv2.imshow("Frame", frame)if cv2.waitKey(1) == 27:breakcv2.destroyAllWindows()
cap.release()