As the number of stranger-on-stranger crimes increases, solving these crimes becomes more exigent. In this milieu, making a sketch of a criminal with the help of forensic science has increasingly become a vital tool in identifying the perpetrator(s) of a crime. But memory about the culprit is always better, the less time has elapsed from exposure to test. For, memory of an event deteriorates over time and, therefore, the earliest session of sketch-making is better than a later one. But generally what happens that the victim or the eyewitness is unable to describe the facial anatomy of criminal(s) as adequately as is required, as the victim or the eyewitness may not have seen the criminal(s) as closely and vividly as is required or the memory may have faded with the elapse of time. This results in a flawed sketch of the criminal(s) despite arduous, pain-staking long hours for creating a sketch. And hence, the criminal(s) may be roaming through the streets of your city to commit another crime.
But now, having overcome such hurdles, Dr Christopher Solomon of the University of Kent in Canterbury, England, has presented a software, called the EFIT-V system, at the Optical Society of America’s (OSA)’s Annual Meeting, Frontiers in Optics (FiO), held in San Jose, California, USA, recently. This software will provide an edge to law-enforcement agencies over the criminals, who will be having a harder time hiding their faces, as this new software helps the victim or the eyewitness recreate and recognise suspects using principles borrowed from the fields of optics and genetics.
In a press release, the OSA pointed out that 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.
Law-enforcement agencies around the world traditionally employ sketch artists, who piece together faces in a process similar to assembling a Mr. Potato Head toy. The witness describes key features–such as hair length, nose size or sharpness of the chin–and the artist combines them to create a likeness. Some departments now have computer programmes that follow the same approach as these artists, creating facial composites using databases of pre-drawn features. But 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,” says Dr Solomon.
But EFIT-V system generates its own faces that progressively evolve to match the victim’s or eyewitness’ memories. The victim’s or eyewitness 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 victim’s or eyewitness 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,” reveals Solomon.
The mathematics underlying the software is borrowed from Dr 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 Dr Solomon.
This software is logically equipped with thorough explanations of facial anatomy, practical methodologies and techniques to forensic artists who work with law-enforcement agencies for perfectly sketching the criminal offenders. The software has now started to make its way to other countries too, where it is being used by researchers in university settings. Meanwhile, Solomon hopes to partner with a suitable company and market the technology to police departments.