Title :
Handprinted Kanji character recognition based on flexible template matching
Author_Institution :
Pattern Recognition Res. Lab., NEC Corp., Kanagawa, Japan
fDate :
30 Aug-3 Sep 1992
Abstract :
Describes a handprinted Kanji character recognition by hierarchical classification based on flexible template matching. In the proposed method, two kinds of flexible template matching are realized by nonlinear shape normalization and by nonlinear pattern matching, based on dynamic programming. The former has the efficiency for local shape restoration and the latter has the efficiency for local shape restoration in handprinted Kanji character variations
Keywords :
dynamic programming; image reconstruction; optical character recognition; dynamic programming; flexible template matching; handprinted Kanji character recognition; hierarchical classification; local shape restoration; nonlinear pattern matching; nonlinear shape normalization; Character recognition; Dynamic programming; Heuristic algorithms; Information technology; National electric code; Nonlinear optics; Optical character recognition software; Pattern matching; Pattern recognition; Shape;
Conference_Titel :
Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on
Conference_Location :
The Hague
Print_ISBN :
0-8186-2915-0
DOI :
10.1109/ICPR.1992.201823
