opencv3 人脸检测和识别

最新推荐文章于 2024-08-02 17:26:38 发布

淮南草

最新推荐文章于 2024-08-02 17:26:38 发布

阅读量975

点赞数

分类专栏： opencv

本文链接：https://blog.csdn.net/zhuisaozhang1292/article/details/80850018

版权

使用OpenCV3进行人脸检测，程序能够准确圈出脸部，但对佩戴眼镜者的眼部检测有限。通过获取人脸特征数据并验证，介绍了在Python环境中安装opencv_contrib_python的步骤。文章探讨了三种人脸识别方法：EigenFace、FisherFace和LBPHFace。

摘要由CSDN通过智能技术生成

人脸部检测

输入：face_detection_still.py

import cv2
from skimage import io

filename = 'people.jpg'

def detect(filename):
  face_cascade = cv2.CascadeClassifier('./cascades/haarcascade_frontalface_default.xml')
  eye_cascade = cv2.CascadeClassifier('./cascades/cascadeshaarcascade_eye.xml')
  img = cv2.imread(filename)
  #gray = io.imread(r"D:\F\eclipse-workspace\imagop\src\faces\vikings.jpg",as_grey=True)
  gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
  #faces = face_cascade.detectMultiScale(gray, 1.3, 5)
  faces = face_cascade.detectMultiScale(gray, 1.3, 9)
  for (x,y,w,h) in faces:
    img = cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
  
  cv2.namedWindow('Vikings Detected!!')
  img = cv2.resize(img, (900, 900), interpolation=cv2.INTER_CUBIC)
  cv2.imshow('Vikings Detected!!', img)
  cv2.imwrite('./vikings.jpg', img)
  cv2.waitKey(0)

detect(filename)

输出：

检测人的脸部和眼睛

'''
Created on 2018年7月1日
      
@author: hcl
'''
import cv2
      
def detect():
    face_cascade = cv2.CascadeClassifier('./cascades/haarcascade_frontalface_default.xml')
    eye_cascade = cv2.CascadeClassifier('./cascades/haarcascade_eye.xml')
    camera = cv2.VideoCapture(0)
    while (True):
        ret,frame = camera.read()
        gray = cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)
        faces = face_cascade.detectMultiScale