What preprocessing image techniques should I take in consideration before applying OpenCV's Viola-Jones method for face recognition ?

Question

Hello,

I am working for a project at school regarding face recognition, based on a technique described by Viola and Jones 2001/2004.

I've read that the OpenCV has an implementation of this algorithm, and it works very good.

I was wondering if you have any advices regarding what techniques (pre-processing) to apply to the images before testing the existence of a face (eg. histogram equalization) ?

Answer 1

I basically used the code from this sample program from the OpenCV page and it worked very well for my masters thesis project. If you get bad results or your lighting is strange you can try a histogram equalization.

Answer 2

Hi Andrei,

with a friend I did something similar too for an university project, and especially on low resolution video sequences it really helped to upsample the frame, doubling its size. It was my friends' idea, who had previously taken an image processing class. Although equivalent, things like decreasing initial scan window size, horizontal and vertical steps didn't produce the same result. In other words it may be better to work on larger images with larger scan windows than on smaller with smaller scan windows. Don't know exactly why.

Bye ;-)