Creating and train the face recognize images

asked 2013-11-23 00:05:04 -0600

Indra gravatar image

Hi, Hi , I am trying to train the images for face recognization code which is there at http://docs.opencv.org/trunk/modules/contrib/doc/facerec/tutorial/facerec_video_recognition.html

Steps followed to create the images . 1.I captured images of three person on webcam 2. I cropped only the faces of the three images

Then I created the sample.csv file , which looks like this

/home/Alog/opencv/img/p12.png;0 /home/Alog/opencv/img/p12.png;0 ... /home/Alog/opencv/img/p21.png;1 /home/Alog/opencv/img/p21.png;1

But I getting the following error when I run the code .

OpenCV Error: Unsupported format or combination of formats (In the Fisherfaces method all input samples (training images) must be of equal size! Expected 307200 pixels, but was 0 pixels.)

It seems I am not giving the proper images .

How to give my own images to train ..?

edit retag flag offensive close merge delete