Autoassociative learning in relaxation labeling networks

Abstract

We address the problem of training relaxation labeling processes, a popular class of parallel iterative procedures widely employed in pattern recognition and computer vision. The approach discussed here is entirely based on a theory of consistency developed by Hummel and Zucker, and contrasts with a recently introduced learning stratery which can be regarded as heteroassociative, i.e., what is actually learned is the association between patterns rather than the patterns themselves. The proposed learning model is instead autoassociative and involves making a set of training patterns consistent, in the sense rigorously defined by Hummel and Zucker, this implies that they become local attractors of the relaxation labeling dynamical system. The learning problem is formulated in terms of solving a system of linear inequalities, and a straightforward iterative algorithm is presented to accomplish this. The attractive feature of this algorithm is that it solves the system when it admits a solution, and automatically yields the best approximation solution when this is not the case. The learning model described here allows one to view the relaxation labeling process as a kind of asymmetric associative memory, the effectiveness of which is demonstrated experimentally.