U.S. researchers say a new technique may soon automatically link hand-drawn police sketches of suspects with mug shot photos in police databases.
Michigan State University researchers have developed a set of algorithms and created software that will automatically match the sketches to existing mug shots in the databases, a university release reported Thursday.
The implications are huge, a researcher says.
We’re dealing with the worst of the worst here,” MSU doctoral student Brendan Klare 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.”
Artists’ sketches are drawn from witness descriptions but unfortunately, Klare said, “often the facial sketch is not an accurate depiction of what the person looks like.”
The project in the MSU Department of Computer Science and Engineering is the first large-scale experiment at matching forensic sketches with photographs.
“Using a database of more than 10,000 mug shot photos, 45 percent of the time we had the correct person,” Klare said.
All of the sketches used were from real crimes where the criminal was later identified.
“We don’t match them pixel by pixel,” Anil Jain, director of the MSU Pattern Recognition and Image Processing lab, said. “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.”
+44 (0) 144-340-8125