|
On Dec 22, 11:31=A0pm, "Badri " <badrionl...@gmail.com> wrote:
> "Nive S" <x...@yahoo.com> wrote in message <gcnf0d$7t...@fred.mathworks.c=
om>...
> > Hi
> > I m doin project in age estimation in matlab. I m extracting features s=
hape 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.
>
> Hi Friend,
> =A0 =A0 =A0 =A0 =A0 =A0We are also doing the same project.We too are stuc=
k in the middle.Can you please help us by providing any source code you hav=
e executed successfully or any source of valuable information(books/weblink=
s) regarding this to my mail id:badrionl...@gmail.com.
> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 Thanks in Advance. =A0
---------------------------------------------------------------------------=
-----------------------------------------------
This may interest you:
http://www.vision-systems.com/display_article/345038/19/none/none/Depar/Vis=
ion-enables-greenhouse-automation
"Imaging software estimates age
"People who hope to keep their age a secret won=92t want to go near a
computer running this software. In addition to performing tasks such
as security control and surveillance monitoring, age-estimation
software also could be used for electronic customer relationship
management or to target specific audiences with advertising, said
Thomas S. Huang, the professor of electrical and computer engineering
at the University of Illinois (Urbana-Champaign, IL, USA; www.illinois.edu)=
.
"Like an age-guesser at a carnival, the computer software can fairly
accurately estimate a person=92s age. But unlike age-guessers, who can
view a person=92s body, the software works by examining only the
person=92s face. Age-recognition algorithms could stop underage drinkers
from entering bars, prevent minors from purchasing tobacco products
from vending machines, and deny children access to adult web sites,
said Huang, who leads the Image Formation and Processing group at the
university=92s Beckman Institute. The software can estimate ages from 1
year to 93 years. The software=92s accuracy ranges from about 50% when
estimating ages to within 5 years, to more than 80% when estimating
ages to within 10 years."
Prof. Thomas Huang'w web site:
http://www.beckman.illinois.edu/directory/t-huang1
100% accuracy is something that can never be achieved because, as you
know, some people just look younger or older than they really are.
For example, they may have wrinkles, sagging facial skin, or hair
color that look like someone of a much different age. So there is a
"visual age appearance" and their "true chronological age." And
they're roughly correlated but there is lots of variance, depending on
genetics, sun exposure, surgical procedures, smoking frequency,
smiling frequency, air temperature and humidity, etc.
Good luck,
ImageAnalyst
|
Feed for this Thread