表情识别

时间：2024-10-19 10:25:00

目标：识别人物的喜悦状态。

一、原理

我们在对一张人脸图片进行关键点定位后，得到每个关键点的位置：

在这里插入图片描述

比如嘴唇，想象一下当一个人大笑的时候，嘴的大小是不是会发生变化呢，上嘴唇关键点与下嘴唇关键点的距离是不是会变化呐？

这样我们就可以通过变化程度来简单的判断人物体现的心情。

唇部关键点：

在这里插入图片描述

人在微笑时，嘴角会上扬，嘴的宽度和与整个脸颊(下颌)的宽度之比变大。

二、代码实现

1. 摄像头前预处理

  1. 构造脸部位置检测器HOG ----> 检测人脸
  2. dlib.shape_predictor载入模型（加载预测器）---- > 获取关键点
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")
cap = cv2.VideoCapture(0)
while True:
    ret, frame = cap.read()  # 如果正确读取，ret为True
    if not ret:
        print("不能读取摄像头")
        break
    faces = detector(frame, 0)  # 检测人脸

2. 计算嘴唇变化

  • 计算嘴的宽高比：

使用euclidean_distances()函数方法，计算两个数据点之间的欧几里得距离，即两点之间的直线距离。

from sklearn.metrics.pairwise import euclidean_distances
def MAR(shape): # 计算嘴的宽高比
    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、脸颊宽度的比值：
def MJR(shape): # 计算嘴宽度、脸颊宽度的比值
    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
  • 代码：
for face in faces:
    shape = predictor(frame,face)
    shape = np.array([[p.x,p.y] for p in shape.parts()])
    mar = MAR(shape) # 绘制右眼凸包
    mjr = MJR(shape) # 绘制左眼凸包
    result = "正常"
    print("mar",mar,"\tmjr",mjr)
    if mar > 0.5:
        result = "大笑"
    elif mjr > 0.45:
        result = "微笑"

3. 绘制嘴唇轮廓

绘制嘴唇轮廓，并将表情检测结果显示在图像上：

def cv2ADDChineseText(img,text,position,textColor=(0,255,0),textSize=30):
    """向图片中添加中文"""
    if (isinstance(img,np.ndarray)):
        img = Image.fromarray(cv2.cvtColor(img,cv2.COLOR_BGR2RGB))
    draw = ImageDraw.Draw(img)

    fontStyle = ImageFont.truetype("simfang.ttf",textSize,encoding="Utf-8")
    draw.text(position,text,textColor,font=fontStyle)
    return cv2.cvtColor(np.asarray(img),cv2.COLOR_BGR2RGB)

mouthHull = cv2.convexHull(shape[48:61]) # 计算凸包
frame = cv2ADDChineseText(frame, result, mouthHull[0, 0])  # 多人脸
cv2.drawContours(frame,[mouthHull],-1,(0,255,0),1)

4. 显示结果

    cv2.imshow("Frame",frame)
    if cv2.waitKey(1) == 27:
        break
cv2.destroyAllWindows()
cap.release()

5. 完整代码展示

import numpy as np
import dlib
import cv2
from sklearn.metrics.pairwise import euclidean_distances
from PIL import Image,ImageDraw,ImageFont

def MAR(shape): # 计算嘴的宽高比
    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

def MJR(shape): # 计算嘴宽度、脸颊宽度的比值
    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

def cv2ADDChineseText(img,text,position,textColor=(0,255,0),textSize=30):
    """向图片中添加中文"""
    if (isinstance(img,np.ndarray)):
        img = Image.fromarray(cv2.cvtColor(img,cv2.COLOR_BGR2RGB))
    draw = ImageDraw.Draw(img)

    fontStyle = ImageFont.truetype("simfang.ttf",textSize,encoding="Utf-8")
    draw.text(position,text,textColor,font=fontStyle)
    return cv2.cvtColor(np.asarray(img),cv2.COLOR_BGR2RGB)

detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")
cap = cv2.VideoCapture(0)
while True:
    ret, frame = cap.read()  # 如果正确读取，ret为True
    if not ret:
        print("不能读取摄像头")
        break
    faces = detector(frame, 0)  # 检测人脸

    for face in faces:
        shape = predictor(frame,face)
        shape = np.array([[p.x,p.y] for p in shape.parts()])
        mar = MAR(shape) # 绘制右眼凸包
        mjr = MJR(shape) # 绘制左眼凸包
        result = "正常"
        print("mar",mar,"\tmjr",mjr)
        if mar > 0.5:
            result = "大笑"
        elif mjr > 0.45:
            result = "微笑"
        mouthHull = cv2.convexHull(shape[48:61])

        frame = cv2ADDChineseText(frame, result, mouthHull[0, 0])  # 多人脸
        cv2.drawContours(frame,[mouthHull],-1,(0,255,0),1)

    cv2.imshow("Frame",frame)
    if cv2.waitKey(1) == 27:
        break
cv2.destroyAllWindows()
cap.release()

相关文章