ABSTRACT
David Marr, an early pioneer in computer vision, defined vision as extracting “. . . from images of the external world, a description that is useful for the viewer and not cluttered with irrelevant information” [Marr, 1982]. Advances in computers and video technology in the past decades have created the expectation that artificial vision should be realizable. The nontriviality of the task is evidenced by the continuing proliferation of new and different approaches to computer vision without any observable application in our everyday lives. Actually, computer vision is already offering practical solutions in industrial assembly and inspection, as well as for military and medical applications; so it seems we are beginning to master some of the fundamentals. However, we have a long way to go to match the vision capabilities of a 4-yearold child. In this chapter, we explore what is known about how nature has succeeded at this formidable task — that of interpreting the visual world.
