A ROBUST BOUNDARY-BASED OBJECT RECOGNITION IN OCCLUSION ENVIRONMENT BY HYBRID HOPFIELD NEURAL NETWORKS

This paper presents a new method of occluded object matching for machi ne vision applications. The current methods for occluded object matchi ng lack robustness and require high computational effort. In this pape r, a new Hybrid Hopfield Neural Network (HHN) algorithm, which combine s the advantages of both a Continuous Hopfield Network (CHN) and a Dis crete Hopfield Network (DHN), will be described and applied for partia lly occluded object recognition in a multi-context scenery. The HHN pr oposed as a new approach provides great fault tolerance and robustness and requires less computation time. Also, advantages of HHN such as r eliability and speed will be discussed. Copyright (C) 1996 Pattern Rec ognition Society.