A new approach to on-line handwritten Chinese character recognition

By adopting several techniques of offline handwritten Chinese character recognition (HCCR), a new approach is proposed for online HCCR. First, an online handwritten Chinese character (HCC) sample library is built. Then, a five layer representation model of HCC based on attributed structural relationships among line segments is proposed. A kind of recognition device called a detector is designed to detect and identify line segments and their relationships. Finally, a recognition network composed of detectors is introduced. This approach solves the problems of stroke order variation, stroke number variation, and some kinds of connective strokes. An online HCCR system based on this approach has perfectly solved the above-mentioned problem with an average recognition rate more than 93% for unlearned handwriting and with real-time response.