Page 1 of 1

Match Sketch(Drawing) face photo to digital color photo

Posted: 2013-10-25T10:40:17-07:00
by Andrea0001
hey guys

im going to match the sketch face (drawing photo) in to the color photo. so for the research i want to find out what are the challenges that matching sketch drawing in to color faces. for now i have find out that

1. resolution pixel difference 2. texture difference 3. distance difference 4. and color (not much effect)

i wanna know that in technical terms what are other challenges and what are available OPEN CV and JAVA CV method and algorithms to overcome that challenges????

please tell me the answers very soon hope some experts will help me thanx

Re: Match Sketch(Drawing) face photo to digital color photo

Posted: 2013-10-25T10:48:21-07:00
by fmw42
First this is an Imagemagick forum. Questions about OpenCV probably cannot be answered here, because in general we do not use OpenCV and know very little about it. Some other uses who do use it may be able to help further.

Second, and example would help.

You probably would be better extracting the edges from the color image and matching those to your sketch. You will need to ensure that the two images have the same scale and rotation. Most comparison techniques are not scale or rotation invariant. IM has the function compare to do the the comparison.

See
http://www.imagemagick.org/Usage/compare/
http://www.imagemagick.org/script/compare.php

And for extracting edges, see
http://www.imagemagick.org/Usage/convolve/#edgedet

IM has no texture functions per se. But you may be able to process with multiple commands to get texure measures. But I have not tried to do that.

Re: Match Sketch(Drawing) face photo to digital color photo

Posted: 2013-10-25T11:29:47-07:00
by Andrea0001
thanx for your reply

im searching for the general solution as i mentioned here i want to know what are the challenges that can come when trying to match sketch face to color face photo. i want to know this in image processing view. and how about fisher face algorithm nad what is the difference between linear discriminant analysis and principle component analysis how can linear discriminant analysis help to extract features in this problem