A COMPUTATIONAL STRUCTURE FOR PREATTENTIVE PERCEPTUAL ORGANIZATION - GRAPHICAL ENUMERATION AND VOTING METHODS

We present an efficient computational structure for preattentive perce ptual organization. By perceptual organization we refer to the ability of a vision system to organize features detected in images based on v iewpoint consistency and other Gestaltic perceptual phenomena. This us ually has two components, a primarily bottom up preattentive part and a top down attentive part, with meaningful features emerging in a syne rgistic fashion from the original set of (very) primitive features. In this work we advance a computational structure for preattentive perce ptual organization. We propose a hierarchical approach, using voting m ethods to build associations through consensus and relational graphs t o represent the organization at each level. The voting method is very efficient in terms of time and space and performs impressively for a w ide range of organizations. The graphical representation allows the re ady extraction of higher order features, or perceptual tokens, because the relational information is rendered explicit.