<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/237323</link>
    <title>MATLAB Central Newsreader - shape &amp;  texture extraction from face image</title>
    <description>Feed for thread: shape &amp;  texture extraction from face image</description>
    <language>en-us</language>
    <copyright>&amp;copy;1994-2012 by MathWorks, Inc.</copyright>
    <webmaster>webmaster@mathworks.com</webmaster>
    <generator>MATLAB Central Newsreader</generator>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <ttl>60</ttl>
    <image>
      <title>MathWorks</title>
      <url>http://www.mathworks.com/images/membrane_icon.gif</url>
    </image>
    <item>
      <pubDate>Fri, 10 Oct 2008 11:41:01 -0400</pubDate>
      <title>shape &amp;  texture extraction from face image</title>
      <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/237323#604624</link>
      <author>Nive S</author>
      <description>Hi&lt;br&gt;
I m doin project in age estimation in matlab. I m extracting features shape and texture from face image, can anyone have idea of doing this if so , please help me moreover i m new to this area and matlab.</description>
    </item>
    <item>
      <pubDate>Fri, 10 Oct 2008 12:39:02 -0400</pubDate>
      <title>Re: shape &amp;  texture extraction from face image</title>
      <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/237323#604632</link>
      <author>Dave Robinson</author>
      <description>&quot;Nive S&quot; &amp;lt;xyz@yahoo.com&amp;gt; wrote in message &amp;lt;gcnf0d$7tn$1@fred.mathworks.com&amp;gt;...&lt;br&gt;
&amp;gt; Hi&lt;br&gt;
&amp;gt; I m doin project in age estimation in matlab. I m extracting features shape and texture from face image, can anyone have idea of doing this if so , please help me moreover i m new to this area and matlab.&lt;br&gt;
&lt;br&gt;
Something I have never tried - so this will need some research on your part.&lt;br&gt;
&lt;br&gt;
1) Switch your colour space to normalized Red, human skin is relatively racially invariant in this space.&lt;br&gt;
&lt;br&gt;
2) Use a threshold value to isolate the face - you will need to experiment to find the optimum value, from this form a binary image (or mask) of the facial position, and extract a greyscale image of the original face.&lt;br&gt;
&lt;br&gt;
3) Look up Law's texture analysis on the web, to undertake a texture estimation on the web.&lt;br&gt;
&lt;br&gt;
4) Alternatively investigate the use of Wavelets, I would imagine that the 'wrinkles' on an old persons face would provide more information in the fine scale regions than would a smooth skin of a young person - of course you may get thrown by beards etc.&lt;br&gt;
&lt;br&gt;
5) Investigate neural nets for processing the texture/wavelet data for age classification.&lt;br&gt;
&lt;br&gt;
Hope that helps&lt;br&gt;
&lt;br&gt;
Dave Robinson</description>
    </item>
    <item>
      <pubDate>Tue, 23 Dec 2008 04:31:04 -0500</pubDate>
      <title>Re: shape &amp;  texture extraction from face image</title>
      <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/237323#618494</link>
      <author>Badri </author>
      <description>&quot;Nive S&quot; &amp;lt;xyz@yahoo.com&amp;gt; wrote in message &amp;lt;gcnf0d$7tn$1@fred.mathworks.com&amp;gt;...&lt;br&gt;
&amp;gt; Hi&lt;br&gt;
&amp;gt; I m doin project in age estimation in matlab. I m extracting features shape and texture from face image, can anyone have idea of doing this if so , please help me moreover i m new to this area and matlab.&lt;br&gt;
&lt;br&gt;
Hi Friend,&lt;br&gt;
&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;We are also doing the same project.We too are stuck in the middle.Can you please help us by providing any source code you have executed successfully or any source of valuable information(books/weblinks) regarding this to my mail id:badrionlion@gmail.com.&lt;br&gt;
&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;Thanks in Advance.  </description>
    </item>
    <item>
      <pubDate>Tue, 23 Dec 2008 05:15:27 -0500</pubDate>
      <title>Re: shape &amp; texture extraction from face image</title>
      <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/237323#618497</link>
      <author>ImageAnalyst</author>
      <description>On Dec 22, 11:31=A0pm, &quot;Badri &quot; &amp;lt;badrionl...@gmail.com&amp;gt; wrote:&lt;br&gt;
&amp;gt; &quot;Nive S&quot; &amp;lt;x...@yahoo.com&amp;gt; wrote in message &amp;lt;gcnf0d$7t...@fred.mathworks.c=&lt;br&gt;
om&amp;gt;...&lt;br&gt;
&amp;gt; &amp;gt; Hi&lt;br&gt;
&amp;gt; &amp;gt; I m doin project in age estimation in matlab. I m extracting features s=&lt;br&gt;
hape and texture from face image, can anyone have idea of doing this if so =&lt;br&gt;
, please help me moreover i m new to this area and matlab.&lt;br&gt;
&amp;gt;&lt;br&gt;
&amp;gt; Hi Friend,&lt;br&gt;
&amp;gt; =A0 =A0 =A0 =A0 =A0 =A0We are also doing the same project.We too are stuc=&lt;br&gt;
k in the middle.Can you please help us by providing any source code you hav=&lt;br&gt;
e executed successfully or any source of valuable information(books/weblink=&lt;br&gt;
s) regarding this to my mail id:badrionl...@gmail.com.&lt;br&gt;
&amp;gt; =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 Thanks in Advance. =A0&lt;br&gt;
&lt;br&gt;
---------------------------------------------------------------------------=&lt;br&gt;
-----------------------------------------------&lt;br&gt;
This may interest you:&lt;br&gt;
&lt;a href=&quot;http://www.vision-systems.com/display_article/345038/19/none/none/Depar/Vis=&quot;&gt;http://www.vision-systems.com/display_article/345038/19/none/none/Depar/Vis=&lt;/a&gt;&lt;br&gt;
ion-enables-greenhouse-automation&lt;br&gt;
&lt;br&gt;
&quot;Imaging software estimates age&lt;br&gt;
&lt;br&gt;
&quot;People who hope to keep their age a secret won=92t want to go near a&lt;br&gt;
computer running this software. In addition to performing tasks such&lt;br&gt;
as security control and surveillance monitoring, age-estimation&lt;br&gt;
software also could be used for electronic customer relationship&lt;br&gt;
management or to target specific audiences with advertising, said&lt;br&gt;
Thomas S. Huang, the professor of electrical and computer engineering&lt;br&gt;
at the University of Illinois (Urbana-Champaign, IL, USA; www.illinois.edu)=&lt;br&gt;
.&lt;br&gt;
&lt;br&gt;
&quot;Like an age-guesser at a carnival, the computer software can fairly&lt;br&gt;
accurately estimate a person=92s age. But unlike age-guessers, who can&lt;br&gt;
view a person=92s body, the software works by examining only the&lt;br&gt;
person=92s face. Age-recognition algorithms could stop underage drinkers&lt;br&gt;
from entering bars, prevent minors from purchasing tobacco products&lt;br&gt;
from vending machines, and deny children access to adult web sites,&lt;br&gt;
said Huang, who leads the Image Formation and Processing group at the&lt;br&gt;
university=92s Beckman Institute. The software can estimate ages from 1&lt;br&gt;
year to 93 years. The software=92s accuracy ranges from about 50% when&lt;br&gt;
estimating ages to within 5 years, to more than 80% when estimating&lt;br&gt;
ages to within 10 years.&quot;&lt;br&gt;
&lt;br&gt;
Prof. Thomas Huang'w web site:&lt;br&gt;
&lt;a href=&quot;http://www.beckman.illinois.edu/directory/t-huang1&quot;&gt;http://www.beckman.illinois.edu/directory/t-huang1&lt;/a&gt;&lt;br&gt;
&lt;br&gt;
100% accuracy is something that can never be achieved because, as you&lt;br&gt;
know, some people just look younger or older than they really are.&lt;br&gt;
For example, they may have wrinkles, sagging facial skin, or hair&lt;br&gt;
color that look like someone of a much different age.  So there is a&lt;br&gt;
&quot;visual age appearance&quot; and their &quot;true chronological age.&quot;  And&lt;br&gt;
they're roughly correlated but there is lots of variance, depending on&lt;br&gt;
genetics, sun exposure, surgical procedures, smoking frequency,&lt;br&gt;
smiling frequency, air temperature and humidity, etc.&lt;br&gt;
&lt;br&gt;
Good luck,&lt;br&gt;
ImageAnalyst</description>
    </item>
    <item>
      <pubDate>Wed, 21 Jan 2009 08:42:02 -0500</pubDate>
      <title>Re: shape &amp;  texture extraction from face image</title>
      <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/237323#622893</link>
      <author>Badri </author>
      <description>&quot;Dave Robinson&quot; &amp;lt;dave.robinson@somewhere.biz&amp;gt; wrote in message &amp;lt;gcnid6$d9f$1@fred.mathworks.com&amp;gt;...&lt;br&gt;
&amp;gt; &quot;Nive S&quot; &amp;lt;xyz@yahoo.com&amp;gt; wrote in message &amp;lt;gcnf0d$7tn$1@fred.mathworks.com&amp;gt;...&lt;br&gt;
&amp;gt; &amp;gt; Hi&lt;br&gt;
&amp;gt; &amp;gt; I m doin project in age estimation in matlab. I m extracting features shape and texture from face image, can anyone have idea of doing this if so , please help me moreover i m new to this area and matlab.&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; Something I have never tried - so this will need some research on your part.&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; 1) Switch your colour space to normalized Red, human skin is relatively racially invariant in this space.&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; 2) Use a threshold value to isolate the face - you will need to experiment to find the optimum value, from this form a binary image (or mask) of the facial position, and extract a greyscale image of the original face.&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; 3) Look up Law's texture analysis on the web, to undertake a texture estimation on the web.&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; 4) Alternatively investigate the use of Wavelets, I would imagine that the 'wrinkles' on an old persons face would provide more information in the fine scale regions than would a smooth skin of a young person - of course you may get thrown by beards etc.&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; 5) Investigate neural nets for processing the texture/wavelet data for age classification.&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; Hope that helps&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; Dave Robinson&lt;br&gt;
&lt;br&gt;
hi Mr.Dave,&lt;br&gt;
&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;we are students, we r doin age estimation project We have done face&lt;br&gt;
&amp;nbsp;detection,face normalization.how to perform wavelet transform to  facial regions images(which transform eg fourier  can you help with function names.?how 2 extract &lt;br&gt;
wrinkles ???&lt;br&gt;
&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;thanx in advance</description>
    </item>
  </channel>
</rss>

