《计算机视觉》—— 表情识别

根据计算眼睛、嘴巴的变化，判断是什么表情
结合以下两篇文章来理解表情识别的实现方法
- 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

完整代码如下：

python 复制代码

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) / C
    return 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:
        break

cv2.destroyAllWindows()
cap.release()