Vision as Computation, or: Does a Computer Vision System Really Assign Meaning to Images?

Computer vision (or image understanding) is generally defined as the construction of explicit, meaningful descriptions of the structure and the properties of the three-dimensional world from two-dimensional images. A conceptual framework for image understanding that is widely accepted is based on Marr’s concept of visual perception as computational process (Marr 1982). Marr postulated a hierarchical architecture for vision systems with different intermediate representations and processing levels (low, middle, and higher level vision). The methodology introduced by Marr — description of cognitive processes on the levels of computational theory, algorithm, and implementation — serves as a guideline, even today, for the “classica”, symbolic AI and the cognitivist paradigm of Cognitive Science, respectively.