Deakin University researchers face up to national security

An improved technique for estimating a person's age that will have implications for national security, law enforcement and restricting children's access to inappropriate web sites has been developed by Deakin University researchers.

The Head of Deakin's School of Engineering and Information Technology, Professor Kate Smith-Miles, and PhD student Xin Geng are working on the automatic age estimation project known as AGES (AGing pattErn Subspace). Using mathematical algorithms, the AGES technique has proven to be more accurate in estimating age based on photographs of people's faces than other existing methods.

"While recognition of most facial variations, such as identity, expression and gender, has been extensively studied, automatic age estimation has rarely been explored," Professor Smith-Miles said.

"In contrast to other facial variations, aging presents several unique characteristics which make age estimation a challenging task."

Logging on to inappropriate websites by under-age computer users would be more difficult with the AGES technique able to determine whether the face of the person at the keyboard conforms with the age they say they are, Professor Smith-Miles said.

"That's just one practical and obvious way in which the work we're doing could be used," she said.

Other applications include:
* Age-specific human-computer interaction which would allow computers to estimate a user's age and automatically choose the vocabulary, interface and services suitable to the user.
* Multi-cue identification/verification where the AGES method could be used in conjunction with other widely used biometric trains like fingerprints and iris recognition to improve security.
* Law enforcement where automatic age estimation could help police determine the age of a suspect more accurately and efficiently:
* Understanding the aging process where the automatic age estimation algorithms could provide valuable help to researchers in psychology, medicine and other fields about the aging procedure or the perception of aging variation.

Professor Smith-Miles said that the AGES method had proven to be more accurate than other systems in estimating age—it even performed better than humans.

"In extensive experiments of over 2000 faces, our method outperformed the existing approaches, and even outperformed human perception of age estimates when the humans were given only the same tightly cropped face images to view as those fed into our algorithm," she said.

"When humans are given wider shots of faces, including hair and clothing, their ability to estimate age is much improved, but without those extra cues our algorithm performs better than humans at age estimation."

A paper co-authored by Professor Smith-Miles and Xin Geng with Professor Zhou Zhi-Hua from China's Nanjing University has been published in the December edition of the prestigious American-based journal – IEEE Transaction on Pattern Analysis and Machine Intelligence.