Face Recognition / Iris Recognition

I have been given the project to research face regonition

Here is example of what I am looking to do:

take a digital picture, be able to automatically Crop and center the head, and be able to find the IRIS of the eye and then put a mask over it, all automated.

I am not asking how to do that, but what software apps would I use to get the job done.

I have found:

 The Mathworks, Inc. (makers of Matlab)  at least $1900 from what I saw # Octave (free alternative to Matlab)  http://www.octave.org/octave.html
# TeLa (free alternative to Matlab)    http://www.ava.fmi.fi/prog/tela.html
# RLaB (free alternative to Matlab)    http://rlab.sourceforge.net/ Not recommended because no longer being developed
# Scilab (free alternative to Matlab)  http://www-rocq.inria.fr/scilab/

But I am not sure if these are the right track for what I need to do.


Who is Participating?
I wear a lot of hats...

"The solutions and answers provided on Experts Exchange have been extremely helpful to me over the last few years. I wear a lot of hats - Developer, Database Administrator, Help Desk, etc., so I know a lot of things but not a lot about one thing. Experts Exchange gives me answers from people who do know a lot about one thing, in a easy to use platform." -Todd S.


Maybe take a look at VisiQuest: http://www.accusoft.com/imaging/visiquest/home.asp
Attrasoft: http://www.attrasoft.com/

That is a tough one....I think people have spent entire Ph.D.'s just working on parts of that, and unless you're able to make the pictures pretty consistent in terms of positioning, I doubt if you'll be able to get very far.

As for the math programs, those are all good choices, matlab probably being the best, but somewhat expensive. As far as the other packages, I would recommend Octave and Scilab, although if you're working on Windows, octave is harder to install. I've never actually used Scilab, but I have used the other two and recommend them. Matlab in particular has quite a bit of image processing code available.

If your pictures are somewhat predictable, you may just be able to crop within a given area, and then recognize the face by identifying pixel color or something (the best would probably be to have a background that is nothing like any skin color). On the other hand, I might be really impressed by what's possible, so don't cut yourself short I guess.

You sound serious about solving this problem,so I assume you must be a pretty mathematical/scientific person. If so, you might get some milage out of these websites, at least for starting ideas:


Hope that helps,

Experts Exchange Solution brought to you by

Your issues matter to us.

Facing a tech roadblock? Get the help and guidance you need from experienced professionals who care. Ask your question anytime, anywhere, with no hassle.

Start your 7-day free trial

Morph Man can line up your chosen areas and morph the mask on in steps and save as animation. Also does layer morphing.

MorphMan 4.0 is the newest release of the most powerful morphing application for PC. This version introduces layers which allow for creation of sophisticated morphing effects and easier integration with video compositing tools. Use full power of fast morphing algorithms, onion skin interface, live preview, vector shape tools, edge detection, and motion estimation for creation of hi-end photo-to-photo and video-to-video morphing.


It's more than this solution.Get answers and train to solve all your tech problems - anytime, anywhere.Try it for free Edge Out The Competitionfor your dream job with proven skills and certifications.Get started today Stand Outas the employee with proven skills.Start learning today for free Move Your Career Forwardwith certification training in the latest technologies.Start your trial today
Web Graphics Software

From novice to tech pro — start learning today.

Question has a verified solution.

Are you are experiencing a similar issue? Get a personalized answer when you ask a related question.

Have a better answer? Share it in a comment.