MARCH 6--Massachusetts Institute of Technology (MIT; Cambridge, MA, USA; web.mit.edu) scientists have applied a computer model of how the brain processes visual information to a complex, real-world task: recognizing the objects in a busy street scene. "People have been talking about computers imitating the brain for a long time," said Tomaso Poggio, the Eugene McDermott professor of brain and cognitive sciences and a member of the McGovern Institute for Brain Research at MIT. "Our work is biologically inspired computer science," said Poggio.
"We developed a model of the visual system that was meant to be useful for neuroscientists in designing and interpreting experiments but that also could be used for computer science," said Thomas Serre, a postdoctoral associate in Poggio's lab and lead author of a paper on the work in the March 2007 IEEE Transactions on Pattern Analysis and Machine Intelligence."We chose street-scene recognition as an example because it has a restricted set of object categories, and it has practical social applications," said Serre. The IEEE paper describes how the team "showed" the model randomly selected images so that it could "learn" to identify commonly occurring features in real-word objects such as trees and people. In so-called supervised training sessions, the model used those features to label by category examples of objects found in digital photographs of street scenes, such as buildings and cars.
Compared to traditional computer-vision systems, the biological model was versatile. Traditional systems are engineered for specific object classes. For instance, systems engineered to detect faces or recognize textures are poor at detecting cars. In the biological model, the same algorithm can learn to detect widely different types of objects.
To test the model, the team presented full street scenes consisting of previously unseen examples from a street-scene database. The model scanned the scene and, based on its supervised training, recognized the objects in the scene. The upshot is that the model was able to learn from examples. This, according to Poggio, is a hallmark of artificial intelligence.
Teaching a computer how to recognize objects has been difficult because a computer model has two paradoxical goals. It needs to create a representation for a particular object that is very specific, such as a horse as opposed to a cow or a unicorn. At the same time the representation must be sufficiently "invariant" so as to discard meaningless changes in pose, illumination and other variations in appearances.
Even a child's brain handles these contradictory tasks easily in rapid object recognition. Pixel-like information enters from the retina and passes through the hierarchical architecture of the visual cortex. What makes the Poggio lab's model powerful is that, computationally speaking, it mimics the brain's own hierarchy. Specifically, the "layers" within the model replicate the way neurons process input and output stimuli according to neural recordings in physiological labs.
For more information, see an article by Cathryn M. Delude, MIT News Office Correspondent, at http://web.mit.edu/newsoffice/2007/surveillance.html.
