Computers can recognise Mr Average
Monday, 28 January 2008 Tracy Staedter
Discovery News

--------------------------------------------------------------------------------

Researchers have found a way to enable computers to boast that, like humans, they never forget a face.

The researchers have developed an imaging technique that merges several photos of the same person into one composite.

They found when composites of different people were shown to a computer it was able recognise all of them.

Such a method could improve face recognition programs already in use to identify suspects at airports, for example, or as part of immigration and employment verification.

"Keep the machines that you're using but give them a different input and that will improve their performance radically," says lead researcher Dr Rob Jenkins, of the University of Glasgow.

Jenkins and university colleague Professor Mike Burton report their findings in the latest issue of the journal Science.

Jenkins and Burton stumbled upon the technique as part of their psychology research.

They were studying the fact that although humans are great at recognising photographed images of people they know, they are less successful at picking out photos of people they do not know.

In this regard, humans and computers struggle with the same issues.

Varied light conditions, expressions, unusual face angles and diverse ages all conspire against positive recognition.

In short, 10 images of one stranger can look like 10 photos of 10 different people.

But when the researchers morphed several photos of the same person, the averaged look was easier for people to discern when comparing it with another image of the person.

Jenkins and Burton theorised it might be easier for a computer to make the connection as well.

So they tested their technique using the public Web site, MyHeritage.com, which runs an industry-standard recognition software called FaceVACS, used in the Australian Customs Service


SmartGate system at Sydney Airport.
The site contains more than 31,000 photos of celebrities.

Users can upload images of their faces and let FaceVACS pick out the celebrity they most resemble.

To gauge the general accuracy of FaceVACS, Jenkins and Burton submitted photos of celebrities known to be in the MyHeritage database.

Of 459 images, the program correctly identified about half.

Huge leap
But when the researchers used those photos to create composites of the celebrities and then submitted those to the Web site, FaceVACS correctly identified every one.

"The performance shot up to 100%," says Jenkins.

"This is a huge leap in a field where people get quite excited about improvements of 2% or 3%."

"It's a new approach that not many people have studied," says Jonathon Phillips, an expert in biometric and automatic face recognition systems at the National Institute of Standards and Technology in Maryland, US.

But, he points out, the morphing technique is not yet automated.

Each image must be manually converted to grayscale, rotated, resized and cropped so that critical points on the faces, such as mouth and eye corners line up.

The morphing and recognising processes happen separately.

"The question is how do you combine them into an effective technique?" queries Phillips.

Jenkins and Burton would like to see their method improved upon, but are going back to human experiments to tease out the range of differences people exhibit with their recognition skills.

Psychology researcher Dr Rob Jenkins holds up his current passport photo, left, and his average face image, right, to illustrate how an improved likeness is brought about by the image averaging technique(Source: Markus Bindemann/)