Face Detection using opencv and python

Question

I'm working on Face Detection in OpenCV(2.4.6) and python(2.7). I have a very simple code, but its not giving me the desired output.

This is my code:

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

When I run this code, my webcam will start and it will give me a blank window like this

Then the webcam will turn off, and in the editor I will get an error as follows:

%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

Any suggestions are welcome. Thanks in advance.

Your line: img = cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2) will draw a rectangle in the image, but the return value will be None, so img changes to None and cannot be drawn. Try cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2) Also, that cv2.imshow(name, img) must be outside the for loop — Vipul
– Vipul, Commented May 10, 2014 at 10:51
@VipulSharma I changed my code according to your suggestion, now like the cam is on and the frames are freezing. I'm using Enthought canopy for this, is it the problem with the IDE? — varsha_holla
– varsha_holla, Commented May 12, 2014 at 6:09

berak · Accepted Answer · 2014-05-10 09:26:19Z

3

some webcams need a warmup time, and deliver empty frames on startup. you want to check for that.

also, who said , that cv2.rectangle returns anything ? where did you get that idea ? from 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

edited May 10, 2014 at 9:26

answered May 10, 2014 at 9:04

berak

39.9k9 gold badges96 silver badges92 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

Vipul Over a year ago

yes, cv2.rectangle does not return anything. I also found this same code somewhere in the official documentation of opencv few months ago but now I cannot find it where it was given.

Collectives™ on Stack Overflow

Face Detection using opencv and python

1 Answer 1

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related