DYNAMIC NETWORK FOR IDENTIFICATION OF CHARACTER LOCATIONS USING SELF-ORGANIZED CLUSTERING

This paper proposes a new network that evaluates the locations of targ ets, i.e., target characters, and recognizes them in an image mixed wi th other objects, i.e., noncharacters. This network consists of a self -organized clustering layer, a simple perceptron layer, and a controll er. The purpose of the self-organized clustering is to evaluate the st ochastic characteristics of an input data set; the self-organization i s executed by calculating the distance between stochastic characterist ics in this layer and the stochastic characteristics of an input vecto r. The simple perceptron layer determines the location of a target cha racter and simultaneously recognizes its character by linearly dividin g all outputs given from the self-organized clustering layer. In the p roposed system, the location identification and its recognition of a t arget character can be adaptively performed by using two small differe nt compensative networks. The location identification and its recognit ion of real target characters, which are obtained in printed boards, a re also shown in this paper.