views:

813

answers:

3

I am trying to make an app that detect faces and recognizes it. I made Face detection but I want some idea to when making recognition. I'm using a web cam for tracking and it can detect the face.Then I am taking only the part of the face to a new gray image and comparing it using EigenObjectRecognizer with list of images in database. But it is not giving good result. Some times find some thing wrong,some times nothing.I want to ask that for comparing photos which additional techniques i must implement? Like Histogram equalization or resolution of faces equalization ?

A: 

Check my answer at the link below. There are some links in it that will be helpful to you, mainly the YouTube video I mentioned.

http://stackoverflow.com/questions/2597302/dice-face-value-recognition/2756179#2756179

typoknig
A: 

Eigenfaces will only get you so much further in face recognition. There's a limit with the number of faces you can train. You'll have to look into newer algorithms , check out new papers in this field and implement them.

You can implement the efficiency of Eigenfaces by making sure that all your images are of the same orientation and size. Orientation and position matters a lot. So make sure you apply right transformations before comparison

Ram Bhat
Can you give some definition for new algorithm?
Meko
+2  A: 

I have an OpenCV Face Recognition (Haar Face Detection + Histogram Equalization + Eigenfaces) tutorial and free source code that you could try: http://www.shervinemami.co.cc/faceRecognition.html

Shervin Emami