Deprecated: mysql_connect(): The mysql extension is deprecated and will be removed in the future: use mysqli or PDO instead in /home/virtualw/public_html/Resources/Hosted/Resource.php on line 9
EFIT-V: The Evolved Police Sketch Artist
Not a member yet? Register for full benefits!

Username
Password
EFIT-V: The Evolved Police Sketch Artist

The sketch artist has been a critical law enforcement tool since time immemorial. An incident occurs, and the police are called. When they arrive, they question the victim, or witnesses, to try and build up an image of what the person looks like. If that description does not help, and the suspect remains at large, a photofit is used. This is when the artist sits down with the victim and listens as the perpetrator's facial features are described.

The problem of course comes in describing not the face, but the individual features. How wide was the nose? Did it point at the end? Eyes, not just what colour they were, but how far apart they were. The line of the jaw, the height of the cheekbones. Each feature is extracted separately and drawn in.

Rather than use an artist, as computers evolved, the Efit system appeared. This had a blank face on a computer screen, and a selection of pre-drawn cut-outs to insert. 100,000 different eyes, 100,000 different noses, 100.000 different mouths and so on, building up piece by piece, the face. This was much quicker than drawing it of course, but again relied on the victim being able to remember individual facial features.

It was a better system however, because typically it started with the eyes, and the piercing stare of the perpetrator. Plus, the victim, once the eyes were in place, stared at the face the whole time, as the rest of it was built up, and could compare it to their memory.

Still, there was room for improvement. EFIT-V is an attempt by Christopher Solomon of the University of Kent in Canterbury in the UK, to push the paradigm further. It uses uses feature-based composites, similar to E-fit, but it also uses genetic algorithms to make a selection of several different faces based on the details that can be remembered. The victim looks at the face which most closely fits the perpetrator, and selects it. This face is then used to seed the next selection of nine faces.

Once all the features are in that can de determined - the whole face is not necessary - the program matches and blends skin tones, and builds a photorealistic 3D face from them, and each of the slightly different offerings are also just as photorealistic. Should an issue such as the resulting skin colour turn out to be wrong, that can be adjusted on the fly, always zeroing in on the ideal face; that which is in memory. By using this approach, it takes the emphasis away from individual features, and more towards looking at the whole face, in as much detail as possible.

The software 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.

The software can also start from scratch, working without facial feature descriptions, and generating 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.

The mathematics underlying the software is borrowed from Solomon's experience using optics to image turbulence in the atmosphere in the 1990s. "I then realised that the same technique could be applied to human faces, which in many respects are mathematically similar to turbulent wave fronts," said Solomon.

One advantage of this technique, says Solomon, 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. Traditionally, police sketch artists cannot work with these people. By tapping into recognition instead of recall, "the EFIT-V system proved to be quite effective even when witnesses say they can't describe a person," says Solomon.

The software has now started to make its way to the United States, where it is being used by researchers in university settings. In the future, Solomon hopes to partner with a suitable U.S. company and market the technology to police departments.

References

EFIT-V -: interactive evolutionary strategy for the construction of photo-realistic facial composites

EFIT 5 Flyer (PDF)

Visionmetric

Staff Comments

 


.
Untitled Document .

Warning: Unknown: write failed: Disk quota exceeded (122) in Unknown on line 0

Warning: Unknown: Failed to write session data (files). Please verify that the current setting of session.save_path is correct (/tmp) in Unknown on line 0