Curve description based on directional features and quasi-convexity/concavity

Abstract Qualitative and global features are appropriate for describing the shape of a complex and deformed object rather than quantitative and local features. In particular, quantized directional features and quasi-convexity/concavity are powerful and flexible for describing the shape of handwritten characters. In this paper, we present a method for structural analysis and description of simple (open) arcs or closed curves based on 2 m -directional features ( m = 1,2,3,…) and quasi-convexity/concavity. We show some examples of shape description of handwritten characters and experimental results for selecting the optimal quantization of direction in handwritten character recognition.

[1]  Ching Y. Suen,et al.  Historical review of OCR research and development , 1992, Proc. IEEE.

[2]  Hirobumi Nishida.  Structural Feature Extraction Using Multiple Bases , 1995, Comput. Vis. Image Underst..

[3]  K. Ishii,et al.  Generation of distorted characters and its applications , 1983 .

[4]  Hirobumi Nishida,et al.  Model-based shape matching with structural feature grouping , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[5]  Hirobumi Nishida,et al.  An Algebraic Approach to Automatic Construction of Structural Models , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Hirobumi Nishida,et al.  Algebraic Description of Curve Structure , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  S. Mori,et al.  Structural Analysis and Description of Curves by Quasi-Topological Features and Singular Points , 1992 .