MIT-Vision: Challenges and Prospects
In a fraction of a second, most of us can recognize a face in a crowd, or make out a face from a blurry image. Pawan Sinha focuses on our uncanny ability to recognize faces as a way of getting at one of the key problems of neuroscience: how our brains represent and then encode objects. He theorizes that facial perception is a holistic process: we broadly take in the relationship, for instance, of eyes, nose and mouth. He tested this hypothesis by creating a computer program that could similarly grasp facial structure, and the program was able to “see” a face within a larger picture. In his Hirschfeld Project, Sinha is trying to distill the caricaturists’ understanding about the important landmarks of a face. He’s discovered that you can shrink an image of a face to 13% horizontally or vertically, and it will still be recognizable. Sinha’s work on how the brain perceives faces has immediate application in security surveillance systems, pedestrian-alert systems for cars, and in robotics. But closest to Sinha’s heart is a new project in India, home to 30% of the world’s blind, where he will assist and study children with recovered sight following congenital blindness.
Leave a Reply
Loading ...
