Predicting future appearance
March 14, 2011 by Editor
A computer program that ages photographic images of people’s faces has been developed by Concordia University’s Department of Computer Science and Software Engineering.
Most face-aged images are currently rendered by forensic artists. Although these artists are trained in the anatomy and geometry of faces, they rely on art rather than science.
“We pioneered a novel technique that combines two previous approaches, known as active appearance models (AAMs) and support vector regression (SVR),” says Khoa Luu, a PhD candidate.
Luu used a combination of AAMs and SVR methods to interpret faces and to “teach” aging rules to the computer. Then, he input information from a database of facial characteristics of siblings and parents taken over an extended period. Using this data, the computer can predict an individual’s facial appearance at a future period.
According to Luu, this technology could serve as a new tool in missing-child investigations and matters of national security — an advance that could help to identify missing kids and criminals on the lam.
Luu’s work appears in the volume series Lecture Notes in Computer Science.
Source and/or read more: http://goo.gl/OgLN4
Publisher and/or Author and/or Managing Editor:__Andres Agostini ─ @Futuretronium at Twitter! Futuretronium Book at http://3.ly/rECc