Object Detection: Face Detection using Haar Cascades
利用基于Haar特征的级联分类器实现人脸检测;官方教程
目标
- 学习基于Haar特征的级联分类器(Cascade Callifiers)实现人脸检测;
- 扩展到人眼检测;
基础知识
Paul Viola、Michael Jones: Rapid Object Detection using a Boosted Cascade of Simple Features
OpenCV中提供了训练和检测两个部分;下面的代码主要是检测部分,也就是说利用OpenCV提供的训练好的模型进行检测;OpenCV提供了不少训练好的分类器模型,如人脸、眼睛、笑容,分类器文件位于GitHub;
有关训练的部分会涉及到上面那篇发表在2001年的CVPR上的文章;Haar特征,积分图,还有级联分类器等概念;
OpenCV实现人脸检测
#!/usr/bin/env python
#-*- coding:utf-8 -*-
# @Time : 19-4-21 下午1:08
# @Author : chen
"""
基于Haar特征的级联分类器用于人脸检测
https://docs.opencv.org/4.0.0/d7/d8b/tutorial_py_face_detection.html
"""
import cv2
# 下面两个文件下载地址
# https://github.com/opencv/opencv/tree/master/data/haarcascades
print("[INFO] 加载.xml文件")
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
eye_cascade = cv2.CascadeClassifier('haarcascade_eye.xml')
# 读取图片,并转换成灰度图像
print("[INFO] 转换成灰度图像")
img = cv2.imread('face_2.jpeg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 在灰度图像下检测人脸
print("[INFO] 人脸检测")
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
count = 0
for (x, y, w, h) in faces:
print("[INFO] 检测到第{}张人脸图像".format(count))
count += 1
# 画矩形圈出人脸
cv2.rectangle(img, (x, y), (x+w, y+h), (255, 0, 0), 2)
# 获取人脸灰度图像和彩色图像
roi_gray = gray[y:y+h, x:x+w]
roi_color = img[y:y+h, x:x+w]
# 在人脸灰度图像上检测眼睛位置
eyes = eye_cascade.detectMultiScale(roi_gray)
for (ex, ey, ew, eh) in eyes:
cv2.rectangle(roi_color, (ex, ey), (ex+ew, ey+eh), (0, 255, 0), 2)
cv2.imshow('img', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
从视频流中检测人脸
#!/usr/bin/env python
#-*- coding:utf-8 -*-
# @Time : 19-4-21 下午1:56
# @Author : chen
"""
从视频流中检测人脸位置,眼睛位置
"""
# import the necessary packages
from imutils.video import VideoStream
from imutils.video import FPS
import time
import cv2
# 加载.xml文件
print("[INFO] 加载.xml文件")
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
eye_cascade = cv2.CascadeClassifier('haarcascade_eye.xml')
# 初始化视频流,唤醒摄像头
print("[INFO] 开启摄像头")
vs = VideoStream(src=0).start()
time.sleep(2.0)
# start the FPS throughput estimator
fps = FPS().start()
# loop over frames from the video file stream
while True:
# 捕获视频帧
frame = vs.read()
# 读取图片,并转换成灰度图像
# img = cv2.imread(img)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# 在灰度图像下检测人脸
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x, y, w, h) in faces:
# 画矩形圈出人脸
cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 2)
# 获取人脸灰度图像和彩色图像
roi_gray = gray[y:y + h, x:x + w]
roi_color = frame[y:y + h, x:x + w]
# 在人脸灰度图像上检测眼睛位置
eyes = eye_cascade.detectMultiScale(roi_gray)
for (ex, ey, ew, eh) in eyes:
cv2.rectangle(roi_color, (ex, ey), (ex + ew, ey + eh), (0, 255, 0), 2)
# update the FPS counter
fps.update()
# show the output frame
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
# if the `q` key was pressed, break from the loop
if key == ord("q"):
break
# stop the timer and display FPS information
fps.stop()
print("[INFO] elasped time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))
# do a bit of cleanup
cv2.destroyAllWindows()
vs.stop()