Sketch artist software to give criminals a harder time to hide faces

WASHINGTON - A new software can act as a new age sketch artist for police by helping witnesses recreate and recognize suspects using principles borrowed from the fields of optics and genetics.

Christopher Solomon of the University of Kent in Canterbury, England is all set to introduce the software, called the EFIT-V system, which is being used by approximately 15 police departments in the United Kingdom and by a half dozen European countries, including France and Switzerland.

In field trials conducted by the Derbyshire police force, it led to twice as many identifications of suspects as traditional methods.

Law enforcement agencies around the world traditionally employ sketch artists, who piece together faces, while some departments even have computer programs that follow the same approach in creating facial composites using databases of pre-drawn features.

However, says Solomon, the problem with this approach is that it doesn’t take into account how the memory actually works.

“There’s quite a bit of research in the psychology field suggesting that we’re not so good at this, at recalling and describing a face,” said Solomon.

His software generates its own faces that progressively evolve to match the witness’ memories.

The witness starts with a general description such as “I remember a young white male with dark hair.”

Nine different computer-generated faces that roughly fit the description are generated, and the witness identifies the best and worst matches.

The software uses the best fit as a template to automatically generate nine new faces with slightly tweaked features, based on what it learned from the rejected faces.

“Over a number of generations, the computer can learn what face you’re looking for,” said Solomon.

The mathematics underlying the software is borrowed from Solomon’s experience using optics to image turbulence in the atmosphere in the 1990s.

“I then realized that the same technique could be applied to human faces, which in many respects are mathematically similar to turbulent wavefronts,” said Solomon.

The software integrates this approach with an interactive genetic algorithm that progressively changes the features based on principles borrowed from evolution.

Characteristics such as nose size and chin sharpness are represented as mathematical genes that mutate and with changing features, the witness’ selections guide the evolution of the face.

One advantage of this technique is that it can be used on witnesses who can’t recall details about a suspect — but say that they would remember the face if they saw it again, said Solomon.

The software will be presented at the Optical Society’s (OSA) Annual Meeting, Frontiers in Optics (FiO). (ANI)