Teaching computers to see | David Fleet | TEDxToronto

This talk was given at a local TEDx event, produced independently of the TED Conferences. Vision, and our understanding of what we see, is arguably the most complex of the human senses. Computer scientists have made incredible progress over the last twenty years within the realm of computer vision, but simply seeing isn’t enough. In this TEDxTalk, David Fleet explains that real value of computer vision lies in a machine’s ability to process what it sees and to draw conclusions and inferences from that data — in the same way that humans process visual information. While we’ve all heard that “seeing is believing,” David Fleet asks, “How much of the brain’s phenomenal capacity to learn can we give to computers so that we can believe what they will see?”

David Fleet is a Professor of Computer Science at the University of Toronto, and a Senior Fellow of the Canadian Institute for Advanced Research. He received the PhD in Computer Science from the University of Toronto in 1991, and has published papers on computer vision, image processing, visual perception, and visual neuroscience. He has won numerous awards for his research, including an Alfred P. Sloan Research Fellowship in 1996, and the Koenderink Prize in 2010 for his work with M. Black and H. Sidenbladh on human pose tracking.

About TEDx, x = independently organized event In the spirit of ideas worth spreading, TEDx is a program of local, self-organized events that bring people together to share a TED-like experience. At a TEDx event, TEDTalks video and live speakers combine to spark deep discussion and connection in a small group. These local, self-organized events are branded TEDx, where x = independently organized TED event. The TED Conference provides general guidance for the TEDx program, but individual TEDx events are self-organized.* (*Subject to certain rules and regulations)