Step right up, let the computer look at your face and tell you your age

September 23, 2008

People who hope to keep their age a secret won't want to go near a computer running this software. Like an age-guesser at a carnival, computer software being developed at the University of Illinois can fairly accurately estimate a person's age. But, unlike age-guessers, who can view a person's body, the software works by examining only the person's face.

"Age-estimation software is useful in applications where you don't need to specifically identify someone, such as a government employee, but would like to know their age," said Thomas S. Huang, the William L. Everitt Distinguished Professor of Electrical and Computer Engineering at the U. of I.

For example, 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's Beckman Institute.

Estimating someone's age is not an easy task, even for a computer. That's partly because the aging process is determined not only by a person's genetic makeup, but by many other factors as well, including health, location and living conditions.

"Human faces do convey a significant amount of information, however, and provide important visual cues for estimating age," Huang said. "Facial attributes, such as expression, gender and ethnic origin, play a crucial role in our image analysis."

Consisting of three modules – face detection, discriminative manifold learning, and multiple linear regression – the researchers' age-estimation software was trained on a database containing photos of 1,600 faces.

The software can estimate ages from 1 year to 93 years. The software's accuracy ranges from about 50 percent when estimating ages to within 5 years, to more than 80 percent when estimating ages to within 10 years. The accuracy can be improved by additional training on larger databases of faces, Huang said.

In addition to performing tasks such as security control and surveillance monitoring, age-estimation software also could be used for electronic customer relationship management.

For example, a camera snapping photos of customers could collect demographic data – such as how many adult men and women buy burgers, or what percentage of teenagers purchase a particular soft drink.

Or, combined with algorithms that identify a person's sex, age-estimation software could help target specific audiences for specific advertisements. For example, a store display might advertise a new automobile or boat as a man walks by, or new clothing or cosmetics as a woman walks by.

"All of this can be done without violating anyone's privacy," Huang said. "Our software does not identify specific individuals. It just estimates their ages."

The researchers published their findings in the two journals IEEE Transactions on Multimedia and IEEE Transactions on Image Processing in 2008.

Source: University of Illinois at Urbana-Champaign

Explore further: Where were the whistleblowers in the Volkswagen emissions scandal?

Related Stories

Audit finds slipshod cybersecurity at

September 25, 2015

The government stored sensitive personal information on millions of health insurance customers in a computer system with basic security flaws, according to an official audit that uncovered slipshod practices.

Animators turn to motion capture tech for better results

September 8, 2015

What happens when you combine two learning tracks, of biomechanics with computer science? One result is a learning opportunity for veterinary students. They can make use of motion capture technology to learn, for example, ...

Oculus proclaims dawn of 'virtual reality era'

September 24, 2015

Facebook-owned Oculus VR wooed software makers on Thursday with the promise of a budding "virtual reality era" and an alliance with streaming television powerhouse Netflix.

Recommended for you

On soft ground? Tread lightly to stay fast

October 8, 2015

These findings, reported today, Friday 9th October, in the journal Bioinspiration & Biomechanics, offer a new insight into how animals respond to different terrain, and how robots can learn from them.


Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.