A multi-stage fuzzy classifier for off-line handwritten Chinese character recognition

The decision boundaries in pattern recognition of large scale (PRLS) are usually complex and sometimes it is difficult to get ideal results with only a single classifier. In the paper, based on system integration idea, the method of fuzzy coarse classifying is given and a multi-stage fuzzy classifier is built. The recognition experiments on one level class of 3755 Chinese characters show that this method can largely improve the recognition accuracy. So it is an efficient method for solving PRLS.