RELAXATION LABELING USING AUGMENTED LAGRANGE-HOPFIELD METHOD

A novel relaxation labeling (RL) method is presented based on Augmente d Lagrangian multipliers and the graded Hopfield neural network (ALH). In this method, an RL problem is converted into a constrained optimiz ation problem and solved by using the augmented Lagrangian and Hopfiel d techniques. The ALH method yields results comparable to the best of the existing RL algorithms in terms of the optimized objective values, yet it is more suitable for analog neural implementation. Experimenta l results are presented. (C) 1997 Pattern Recognition Society. Publish ed by Elsevier Science Ltd.