来自:http://www.cnblogs.com/21207-iHome/articles/6253796.html
Haar特征分类器就是一个XML文件,存放在OpenCV安装目录中的\data\ haarcascades目录下
- OpenCV中的Haar级联检测
OpenCV 自带了训练器和检测器。如果你想自己训练一个分类器来检测汽车,飞机等的话,可以使用 OpenCV 构建。其中的细节参考这里:Cascade Classifier Training
现在我们来学习一下如何使用检测器。OpenCV 已经包含了很多已经训练好的分类器,其中包括:面部,眼睛,微笑等。这些 XML 文件保存在/opencv/data/haarcascades/文件夹中。下面我们将使用 OpenCV 创建一个面部和眼部检测器。首先我们要加载需要的 XML 分类器。然后以灰度格式加载输入图像或者是视频。
import sys
import cv2
import cv2.cv as cv
import numpy as np
OPENCV_PATH = r"C:/Program Files/OpenCV2/opencv"
# Cascade classifier class for object detection.
# Python: cv2.CascadeClassifier(filename) -> CascadeClassifier object
# Parameters: filename – Name of the file from which the classifier is loaded.
face_cascade = cv2.CascadeClassifier(OPENCV_PATH + '/data/haarcascades/haarcascade_frontalface_default.xml')
cap = cv2.VideoCapture("test.avi") # 打开视频文件
# Returns true if video capturing has been initialized already
if not cap.isOpened(): # 检测视频是否打开成功
sys.exit()
rate=cap.get(cv.CV_CAP_PROP_FPS) # 获取帧率
delay = int(1000 / rate) # 每一帧之前的延迟与视频的帧率相对应
while(True):
# Capture frame-by-frame
ret, frame = cap.read()
# Our operations on the frame come here
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# Detects objects of different sizes in the input image.
# The detected objects are returned as a list of rectangles
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x,y,w,h) in faces:
cv2.rectangle(frame,(x,y),(x+w,y+h),(255,0,0),2)
# Display the resulting frame
cv2.imshow('frame', frame)
if cv2.waitKey(delay) & 0xFF == ord('q'):
break
# Closes video file or capturing device.
cap.release()
cv2.destroyAllWindows()
下面是对动画片超级大坏蛋中的一个视频片段进行人脸检测:
下面检测照片(1927年第五届索尔维会议)中的多个人脸:
import cv2
OPENCV_PATH = r"C:/Program Files/OpenCV2/opencv"
face_cascade = cv2.CascadeClassifier(OPENCV_PATH + '/data/haarcascades/haarcascade_frontalface_default.xml')
img = cv2.imread('test.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 2)
for (x,y,w,h) in faces:
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
cv2.imshow('image',img)
cv2.waitKey(0)
cv2.destroyAllWindows()