Python3.6.0+opencv3.3.0人脸检测示例

网上有很多关于Python+opencv人脸检测的例子,并大都附有源程序。但是在实际使用时依然会遇到这样或者那样的问题,在这里给出常见的两种问题及其解决方法。

先给出源代码:(如下)

import cv2

import numpy as np

cv2.namedWindow("test")

cap=cv2.VideoCapture(0)

success,frame=cap.read()

classifier=cv2.CascadeClassifier("haarcascade_frontalface_alt.xml")

while success:

success,frame=cap.read()

size=frame.shape[:2]

image=np.zeros(size,dtype=np.float16)

image=cv2.cvtColor(frame,cv2.cv.CV_BGR2GRAY)

cv2.equalizeHist(image,image)

divisor=8

h,w=size

minSize=(w/divisor,h/divisor)

faceRects=classifier.detectMultiScale(image,1.2,2,cv2.CASCADE_SCALE_IMAGE,minSize)

if len(faceRects)> 0:

for faceRect in faceRects:

x,y,w,h=faceRect

cv2.circle(frame,(x+w/2,y+h/2),min(w/2,h/2),(255,0,0))

cv2.circle(frame,(x+w/4,y+h/4),min(w/8,h/8),(255,0,0))

cv2.circle(frame,(x+3*w/4,y+h/4),min(w/8,h/8),(255,0,0))

cv2.rectangle(frame,(x+3*w/4,y+3*h/4),(x+5*w/8,y+7*h/8),(255,0,0))

cv2.imshow("test",frame)

key=cv2.waitKey(10)

c=chr(key&255)

if c in ['q','Q',chr(27)]:

break

cv2.destroyWindow("test")

运行后出现问题一:

Traceback (most recent call last):

File “E:/facepy/m.py”, line 14, in

image=cv2.cvtColor(frame,cv2.cv.CV_BGR2GRAY)

AttributeError: module ‘cv2.cv2' has no attribute ‘cv'

解决方法:

cv2.cv.CV_BGR2GRAY是Opencv 2.x的变量,在Opencv 3.3中无法识别,所以应该替换成:

image=cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)

修改完成后,继续运行,又出现问题二:

Traceback (most recent call last):

File “E:/facepy/m.py”, line 19, in

faceRects=classifier.detectMultiScale(image,1.2,2,cv2.CASCADE_SCALE_IMAGE,minSize)

TypeError: integer argument expected, got float

解决方法:

由于minSize传到detectMultiScale函数的值不是整数导致的导致出现错误,所以这里我们需要强制转换minSize的值为整数: minSize =(w//divisor, h//divisor)  或者 minSize=(int(w/divisor),int(h/divisor))

以上是 Python3.6.0+opencv3.3.0人脸检测示例 的全部内容, 来源链接: utcz.com/z/336694.html

回到顶部