A Handwritten Chinese Address Recognition Method Using Recursive Holistic Word Matching and Edit Distance Based Verification Strategies

With extensive applications in many domains, e.g., in postal address recognition, bank cheque recognition etc, Handwritten Chinese Address Recognition (HCAR) has attracted much interest recently. However, due to the large number in Chinese characters categories, irregular distortion and touching in handwriting, and high variations in writing styles, this task presents a big challenge in the community of pattern recognition. In this paper, we propose a novel three-stage approach to attack the Handwritten Chinese Address Recognition problem. More specifically, we propose the framework of coarse recognition, fine recognition, and verification as well as some new techiqniues tailored to each stage for HCAR. Coarse recognition is designed for speeding up the system; fine recognition exploits a novel recursive and enhanced segmentation-free holistical word recognition method in order to overcome the difficulties in HCAR; verification uses an important modified edit distance definition for further lifting the system accuracy. A series of experiments are conducted to evaluate the proposed novel system. The results demonstrate that our system outperforms other traditional methods in three real data sets.