Face Detection

asked 2014-04-11 14:56:15 -0600

soniak_169 gravatar image

updated 2014-04-11 16:35:32 -0600

Hello,

I am trying to get face detection using haar cascading. I tried it on a live video from my webcam on my own face, that did not work. Then I tried it on a still image, which did not work either. In both cases, the image is shown, but no face is detected. I tried modifying the sample code from the open cv face detection tutorial. Here is the code I tried:

import numpy as np
import cv2

face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
eye_cascade = cv2.CascadeClassifier('haarcascade_eye.xml')

img = cv2.imread('face.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(img, 1.3,5)
print faces
for (x,y,w,h) in faces:
    cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
    roi_gray = gray[y:y+h, x:x+w]
    roi_color = img[y:y+h, x:x+w]
    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)
edit retag flag offensive close merge delete

Comments

but i can already see the problem - you're assuming, the 'haarcascade_frontalface_default.xml' is in the same folder, where your python script starts. that's probably not valid. (more likely it's in opencv's data folder.)

try an absolute path for a change

berak gravatar imageberak ( 2014-04-11 15:14:15 -0600 )edit

Thanks for your answer. I am sorry but I'm not familiar with open cv, but I'm in a situation where I need to use it.

so by absolute path do you mean like this? face_cascade = cv2.CascadeClassifier('C:\Users\sonia\Downloads\opencv\data\haarcascades')

thanks again

soniak_169 gravatar imagesoniak_169 ( 2014-04-11 16:34:54 -0600 )edit

yes, exactly

berak gravatar imageberak ( 2014-04-12 00:35:17 -0600 )edit