Structural Feature Extraction Using Multiple Bases

摘要

The prime difficulty in research and development of the handwritten character recognition systems is in the variety of shape deformations. In particular, throughout more than a quarter of a century of research, it is found that some qualitative features such as quasi-topological features (convexity and concavity), directional features, and singular points (branch points and crossings) are effective in coping with variations of shapes. On the basis of this observation, Nishida and Mort (IEEE Trans. Pattern Anal. Mach. Intell. 14, 1992, 516-533; and Structured Document Image Analysis (H. S. Baird, H. Bunke, and K. Yamamoto, Eds.), pp. 139-187, Springer-Verlag, New York, 1992) proposed a method for structural description of character shapes by few components with rich features. This method is clear and rigorous, can cope with various deformations, and has been shown to be powerful in practice. Furthermore, shape prototypes (structural models) can be constructed automatically from the training data (Nishida and Mori, IEEE Trans. Pattern Anal. Mach. Intell. 15, 1993, 1298-1311). However, in the analysis of directional features, the number of directions is fixed to 4, and more directions such as 8 or 16 cannot be dealt with. For various applications of Nishida and Mori's method, we present a method for structural analysis and description of simple arcs or closed curves based on 2m-directional features (m = 2, 3, 4, ...) and convex/concave features. On the other band, software OCR systems without specialized hardware have attracted much attention recently. Based on the proposed method of structural analysis and description, we describe a software implementation of a handwritten character recognition system using multistage strategy.