A On-line Handwriting Recognition Approach of Chinese Characters for Personal Digital Assistants

Abstract

This paper presents an on-line Chinese character recognition approach for personal digital assistants without writing constraints on both stroke order and stroke number. Stroke correspondence is accomplished via a rule-based approach such that combinatorial exhaustion can be avoided. Then, character distance is computed for character discrimination. For portable information processing systems, such as personal digital assistants (PDAs), the computing resource is very limited. We propose a hierarchical representation to reduce the storage representation. While using the hierarchical reference database, it only requires O (n log n ) time to accomplish stroke correspondence between an input script and a template of n strokes.