Constructing Simple Stable Descriptions for Image

(1) In eeect, Binford 2] calls stability with respect to change in viewpoint the \assump-tion of general position." In this sense, general position is a special case of our notion of stability. (2) An optimal descriptive language is one that minimizes the average number of bits of description per bit of input. This will be discussed in detail shortly. (3) The inequality occurs only because of boundary conditions. Thus, the approximation is best for large regions, where the eeects of boundary conditions are minimal. Abstract A new formulation of the image partitioning problem is presented: construct a complete and stable description of an image, in terms of a speciied descriptive language, that is simplest in the sense of being shortest. We show that a descriptive language limited to a low-order polynomial description of the intensity variation within each region and a chain-code-like description of the region boundaries yields intuitively satisfying partitions for a wide class of images. The advantage of this formulation is that it can be extended to deal with subsequent steps of the image-understanding problem (or to deal with other image attributes, such as texture) in a natural way by augmenting the descriptive language. Experiments performed on a variety of both real and synthetic images demonstrate the superior performance of this approach over partitioning techniques based on clustering vectors of local image attributes and standard edge-detection techniques.