Thaindian News

Washington, Mar 5 (ANI): Police often find it difficult to nab criminals using facial sketches, but a new technique could soon change that - thanks to the efforts led by some Michigan State University researchers.

A team led by Indian-origin scientist Anil Jain, professor of computer science and engineering at MSU, and doctoral student Brendan Klare has developed a set of algorithms that can automatically match hand-drawn facial sketches to mug shots of criminals stored in police databases.

They said that once in use, the implications of their programme would be huge.

“We’re dealing with the worst of the worst here. Police sketch artists aren’t called in because someone stole a pack of gum. A lot of time is spent generating these facial sketches so it only makes sense that they are matched with the available technology to catch these criminals,” said Klare.

“Artists’ sketches are drawn from witness descriptions. Unfortunately, often the facial sketch is not an accurate depiction of what the person looks like,” he added.

The MSU project is the first large-scale experiment at matching operational forensic sketches with photographs and, so far, results have been promising.

“Using a database of more than 10,000 mug shot photos, 45 percent of the time we had the correct person,” said Klare

All of the sketches used were from real crimes where the criminal was later identified.

“We don’t match them pixel by pixel. We match them up by finding high-level features from both the sketch and the photo; features such as the structural distribution and the shape of the eyes, nose and chin,” said Jain.

The MSU team plans to field test the system in about a year.

The research will appear in the March issue of the journal IEEE Transactions on Pattern Analysis and Machine Intelligence. (ANI)