Path: news.mathworks.com!not-for-mail
From: <HIDDEN>
Newsgroups: comp.soft-sys.matlab
Subject: Re: facial features extraction
Date: Sun, 7 Jun 2009 19:59:02 +0000 (UTC)
Organization: The MathWorks, Inc.
Lines: 50
Message-ID: <h0h666$p98$1@fred.mathworks.com>
References: <ffb3c486-32aa-45dc-8157-1c2b27e8b991@s31g2000vbp.googlegroups.com> <ac50e2c9-af38-429f-b802-b1dce77aec25@v4g2000vba.googlegroups.com> <aFmPl.15718$jZ1.2434@flpi144.ffdc.sbc.com> <guktq2$jf6$1@fred.mathworks.com> <z0nPl.15719$jZ1.1919@flpi144.ffdc.sbc.com>
Reply-To: <HIDDEN>
NNTP-Posting-Host: webapp-02-blr.mathworks.com
Content-Type: text/plain; charset="ISO-8859-1"
Content-Transfer-Encoding: 8bit
X-Trace: fred.mathworks.com 1244404742 25896 172.30.248.37 (7 Jun 2009 19:59:02 GMT)
X-Complaints-To: news@mathworks.com
NNTP-Posting-Date: Sun, 7 Jun 2009 19:59:02 +0000 (UTC)
X-Newsreader: MATLAB Central Newsreader 1868870
Xref: news.mathworks.com comp.soft-sys.matlab:545366


Thanks Chris. I am trying to do something similar. I need extracted features for analysis in a database. However until now most of the algorithms I have tried have given less than satisfatory results. Do you have suggestions on how I can extract and segment just the eyes and lips?

Thanks
radhika

"Nasser Abbasi" <nma@12000.org> wrote in message <z0nPl.15719$jZ1.1919@flpi144.ffdc.sbc.com>...
> 
> "omar " <ouzizo@gmail.com> wrote in message 
> news:guktq2$jf6$1@fred.mathworks.com...
> > "Nasser Abbasi" <nma@12000.org> wrote in message 
> > <aFmPl.15718$jZ1.2434@flpi144.ffdc.sbc.com>...
> >>
> >> <ouzizo@gmail.com> wrote in message
> >> news:ac50e2c9-af38-429f-b802-b1dce77aec25@v4g2000vba.googlegroups.com...
> >> > guys i forgot to note that i am using matlab for the project so please
> >> > i want to know the method or whatever it is using matlab.
> >> > thanks in advance
> >>
> >> It sounds like you need to look at Principal components analysis ?
> >>
> >> doc  princomp
> >>
> >> google matlab Principal components analysis  you'll find source code and 
> >> web
> >> pages on this
> >>
> >> --Nasser
> >>
> >
> 
> > i googled matlab Principal components analysis and i didnt know what has 
> > this to do with face feature extraction. i have an image and i want to 
> > extract some features from the image.
> 
> Well,  The SECOND link shown under the above search is page full of matlab 
> code for face feature extraction:
> 
> http://www.cs.ait.ac.th/~mdailey/matlab/
> 
> If you just have ONE face, then this might not apply to your problem.
> 
> PCA is used if one has many images, and want to extract the most common or 
> prominant features of all the faces.
> 
> It sounds then may be you need to apply edge detection or something similar.
> 
> good luck
> 
> --Nasser
>