A NOVEL FEATURE RECOGNITION NEURAL-NETWORK AND ITS APPLICATION TO CHARACTER-RECOGNITION

This paper presents a Feature Recognition Network for pattern recognit ion that learns the patterns by remembering their different segments. The base algorithm for this network is a Boolean net algorithm that we developed during our past research. Simulation results show that the network can recognize patterns after significant noise, deformation, t ranslation and even scaling. The network is compared to existing popul ar networks used for the same purpose, especially Neocognitron. The ne twork is also analyzed as regards to interconnection complexity and in formation storage/retrieval.