使用opencv和python进行人脸检测

Question

我正在OpenCV（2.4.6）和python（2.7）中进行人脸检测。我有一个非常简单的代码，但它没有给我所需的输出。

这是我的代码：

import numpy as np
import cv2
cam = cv2.VideoCapture(0)
name = 'detect'
face_cascade = cv2.CascadeClassifier('C:\opencv\data\haarcascades\haarcascade_frontalface_default.xml')
cv2.namedWindow(name, cv2.WINDOW_AUTOSIZE)
while True:
    s, img = cam.read()
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(img, 1.3, 5)
    for (x,y,w,h) in faces:
        img = cv2.rectangle(gray,(x,y),(x+w,y+h),(255,0,0),2)
        cv2.imshow(name, img)    
    k = cv2.waitKey(0)
    if k == 27:
        cv2.destroyWindow(name)
    break

当我运行此代码时，我的网络摄像头将启动，它会给我一个这样的空白窗口

然后网络摄像头将关闭，在编辑器中我将收到如下错误：

%run "D:/6th sem/1.OpenCV + Python/det.py"
---------------------------------------------------------------------------
error                                     Traceback (most recent call last)
C:\Users\HP\AppData\Local\Enthought\Canopy32\App\appdata\canopy-1.3.0.1715.win-x86\lib\site-packages\IPython\utils\py3compat.pyc in execfile(fname, glob, loc)
195             else:
196                 filename = fname
--> 197             exec compile(scripttext, filename, 'exec') in glob, loc
198     else:
199         def execfile(fname, *where):

D:\6th sem\1.OpenCV + Python\det.py in <module>()
  7 while True:
  8     s, img = cam.read()
 ----> 9     gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
 10     faces = face_cascade.detectMultiScale(img, 1.3, 5)
 11     #print s

error: ..\..\..\src\opencv\modules\imgproc\src\color.cpp:3402: error: (-215) scn == 3 || scn == 4

欢迎任何建议。提前谢谢。

Answer 1

某些网络摄像头需要预热时间，并在启动时提供空帧。你想检查一下。

还有，谁说，cv2.rectangle返回任何内容？你在哪里得到这个想法？来自SO？

while cap.isOpened():
    s, img = cam.read()
    if s == None:
        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        faces = face_cascade.detectMultiScale(gray, 1.3, 5) #hmm, 5 required neighbours is actually a lot.
        for (x,y,w,h) in faces:
            cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2) # if you want colors, don't paint into a grayscale...
        cv2.imshow(name, img)    
    k = cv2.waitKey(0)
    if k == 27:
        cv2.destroyWindow(name)
        break