CONFUSION SET RECOGNITION OF ONLINE CHINESE CHARACTERS BY ARTIFICIAL-INTELLIGENCE TECHNIQUE

In this paper, a knowledge based on-line recognition system for the sq uare written Chinese similar characters is presented by utilizing Chin ese character knowledge and artificial intelligence techniques. The re ference patterns are represented by the heuristic knowledge describing them. The knowledge consists of the knowledge primitives designed in the system. For the pattern pair matching made on an unknown pattern, the matching recognition is made by utilizing problem reduction strate gy, goal-driven inferencing like matching, and AND-OR tree searching a lgorithm. The method is developed and concatenated to a first on-line recognition system specially for recognizing similar characters. The r ecognized similar characters to be researched in the experimental syst em are chosen from the part of the error recognition results of the fi rst system, totally 96 similar characters. The average recognition rat e of 99.9% can be achieved. The results suggest that the knowledge can present efficient distinguishing ability and the method is reasonable and feasible.