Washington, Oct 29 : Women who're not comfortable revealing their age should stay miles away from University of Illinois-developed computer software that reveals a person's age just like humans do-by looking at his or her face.
The software, developed at the University of Illinois, Urbana-Champaign, could analyse an image of your face to verify your identity or run a commercial according to your interest.
"Age measurement is very difficult. If you use the face to estimate age we can really get the apparent age, or how old a person looks," Discovery News quoted Thomas Huang, the lead developer, as saying.
For developing the software, the researchers trained their computer algorithm using 1,600 different people with five pictures of each person, for a total of 8,000 images.
The age of the people in the pictures ranged from one year to 93 years old.
While the computer was not told what to look for, it still searched the faces and used its own software to determine which features best determined the person's apparent age.
One of the features the computer took into account was gray scale- it saw how dark or how light each pixel was compared to other pixels, and then guesses the apparent age of the individual.
"A woman wearing makeup should get a younger age. A smoother skin texture will register as younger-looking," said Huang.
The software also looked at the shape of the face-the relative positions of the eyes, nose, ears, the shape of the mouth, all change over time and can help indicate a person's age.
"If you use the real age as the ''ground truth'', then the accuracy is quite low. But if we estimate [a person's age] to within 10 years, then the accuracy is about 80 percent," said Huang.
He said that face-recognition software might benefit fast food companies that want to know how many male teenagers buy a particular sandwich or clothing companies that could run a different ad catering to people of all age-groups.
"If you can estimate the gender or the age of the viewer you can change the display. For a younger viewer you might want to display one type of commercial, and show a different commercial for an older viewer," said Huang.
Face-recognition software would also be useful for security. The system could tap into existing security cameras to capture images, which would then be run through the software.
Also, Huang is now upgrading his software so that it could read face images at different angles. In his opinion, his software is just as good as humans at age estimation.