NOTE: The following materials are presented for timely dissemination of academic and technical work. Copyright and all other rights therein are reserved by authors and/or other copyright holders. Persoanl use of the following materials is permitted and, however, people using the materials or information are expected to adhere to the terms and constraints invoked by the related copyright.

A Parallel Voting Scheme for Aspect Recovery


Recently, a qualitative approach was proposed for 3-D shape recovery based on a hybrid object representation. In this approach, aspect recovery is the most important stage which binds regions in the image into meaningful aspects to support 3-D primitive recovery. There is no known polynomial time algorithm to solve this problem. The previous approach dealt with this problem by using a heuristic method based on the conditional probability. Unlike the previous method, in this paper, we present a novel parallel voting scheme to conquer the problem for efficiency. For this purpose, the previous global aspect representation is replaced with a distributed representation of aspects. Based on this representation, we propose a three-layer parallel voting network to complete aspect recovery. For evaluating likelihood, a continuous Hopfield net is employed so that we can enumerate all aspect coverings in decreasing order of likelihood. We describe this method in detail and demonstrate its usefulness with simulations.

Click jcst95.pdf for full text