— Biocompatible graphene transistor array reads cellular signals — Researchers have demonstrated, for the first time, a graphene-based transistor array that is compatible with living biological cells and capable of recording the electrical signals…
— Researchers find some smartphone models more vulnerable to attack — New research from North Carolina State University shows that some smartphones specifically designed to support the Android mobile platform have incorporated additional features that…
— MIT: New algorithm may improve defensive driving — In 2008, according to the National Highway Traffic Safety Administration, 2.3 million automobile crashes occurred at intersections across the United States, resulting in some 7,000…
— Researchers use CT to recreate Stradivarius violin — Using computed tomography (CT) imaging and advanced manufacturing techniques, a team of experts has created a reproduction of a 1704 Stradivarius violin. Three-dimensional images of…
— Terminator-style info-vision takes step towards reality — The streaming of real-time information across your field of vision is a step closer to reality with the development of a prototype contact lens that could potentially provide the wearer…
— Scientists invent long-lasting, near infrared-emitting material — Materials that emit visible light after being exposed to sunlight are commonplace and can be found in everything from emergency signage to glow-in-the-dark stickers. But until now,…
— Team of researchers develop world's lightest material — A team of researchers from UC Irvine, HRL Laboratories and the California Institute of Technology have developed the world's lightest material - with a density of 0.9 mg/cc - about…
— Humans can control a cursor with power of thought — The act of mind reading is something usually reserved for science-fiction movies but researchers in America have used a technique, usually associated with identifying epilepsy, for…
— Nanoparticles improve solar collection efficiency — Using minute graphite particles 1000 times smaller than the width of a human hair, mechanical engineers at Arizona State University hope to boost the efficiency - and profitability…
Method developed to match police sketch, mug shot
The long-time practice of using police facial sketches to nab criminals has been, at best, an inexact art. But the process may soon be a little more exact thanks to the work of some Michigan State University researchers.
A team led by MSU University Distinguished Professor of Computer Science and Engineering Anil Jain and doctoral student Brendan Klare has developed a set of algorithms and created software that will automatically match hand-drawn facial sketches to mug shots that are stored in law enforcement databases.
Once in use, Klare said, the implications are huge.
'We're dealing with the worst of the worst here,' he said. '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.'
Typically, artists' sketches are drawn by artists from information obtained from a witness. Unfortunately, Klare said, 'often the facial sketch is not an accurate depiction of what the person looks like.'
There also are few commercial software programs available that produce sketches based on a witness' description. Those programs, however, tend to be less accurate than sketches drawn by a trained forensic artist.
The MSU project is being conducted in the Pattern Recognition and Image Processing lab in the Department of Computer Science and Engineering. It is the first large-scale experiment matching operational forensic sketches with photographs and, so far, results have been promising.
'We improved significantly on one of the top commercial face-recognition systems,' Klare said. 'Using a database of more than 10,000 mug shot photos, 45 percent of the time we had the correct person.'
All of the sketches used were from real crimes where the criminal was later identified.
'We don't match them pixel by pixel,' said Jain, director of the PRIP lab. '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.'
This project and its results appear in the March 2011 issue of the journal IEEE Transactions on Pattern Analysis and Machine Intelligence.
The MSU team plans to field test the system in about a year.
Or subscribe for our Newsletter, a free e-mail publication. It is published practically every day.
Scientists get a grip on colliding fermions to enhance atomic clock accuracy
Ivory tower needs to adapt to online media landscape, scholar says
Sensitive robots
Fitter frames: Nanotubes boost structural integrity of composites