A shape analysis model with applications to a character recognition system
- 2 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 182-189
- https://doi.org/10.1109/acv.1992.240313
Abstract
A method for the recognition of multifont printed characters is proposed, giving emphasis to the identification of structural descriptions of character shapes using prototypes. Noise and shape variations are modeled as series of transformations from groups of features in the data to features in each prototype. Thus, the method manages systematically the relative distortion between a candidate shape and its prototype, accomplishing robustness to noise with less than two prototypes per class, on the average. Our method uses a flexible matching between components and a flexible grouping of the individual components to be matched. A number of shape transformations are defined. Also, a measure of the amount of distortion that these transformations cause is given. The problem of classification of character shapes is defined as a problem of optimization among the possible transformations that map an input shape into prototypical shapes. Some tests with hand printed numerals confirmed the method's high robustness level.<>Keywords
This publication has 11 references indexed in Scilit:
- One view of the methodology in handwriting character recognitionPublished by SPIE-Intl Soc Optical Eng ,1992
- Omnidocument technologiesProceedings of the IEEE, 1992
- Hierarchical attributed graph representation and recognition of handwritten chinese charactersPattern Recognition, 1991
- Structural classification and relaxation matching of totally unconstrained handwritten zip-code numbersPattern Recognition, 1988
- On machine recognition of hand-printed Chinese characters by feature relaxationPattern Recognition, 1988
- On the Recognition of Printed Characters of Any Font and SizePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1987
- Disjoint Paths—A SurveySIAM Journal on Algebraic Discrete Methods, 1985
- A distance measure between attributed relational graphs for pattern recognitionIEEE Transactions on Systems, Man, and Cybernetics, 1983
- Elastic Matching of Line DrawingsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1981
- Structural Descriptions and Inexact MatchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1981