Parameter Nets

This paper describes the nucleus of a connectionist theory of low level and intermediate-level vision. The theory explains segmentation in terms of massively parallel cooperative computation among intrinsic images and a set of feature networks at different levels of abstraction. Explaining how parts of an image are perceived as a meaningful whole or gestalt is a problem central to vision. A stepping stone towards a solution is recent work showing how to calculate images of physical parameters from intensity data. Such images are known as intrinsic images, and examples are images of velocity (optical flow), surface orientation, occluding contour, and disparity. Intrinsic images show great promise; they are distinctly easier to work with than the original intensity image, but they present problems. Their boundary conditions need to he specified, and, more importantly, they are not grouped into objects. This grouping can often be detected by a general Hough transform technique which has the following aspects: possible objects are represented by networks of feature parameters; intrinsic image points are mapped into these networks. This mapping will be many-to-one onto parameter values that represent object features. The virtues of the methodology are that it can handle occlusion and noise and can specify intrinsic image boundaries. Furthermore, it can be made practical for high-dimensional feature spaces