DocumentCode :
1803487
Title :
On the intra-category clustering to make multidictionary patterns for multidictionary template matching method
Author :
Ohkura, Mitsuru ; Shiono, Mitsuru
Author_Institution :
Dept. of Electron. Eng., Okayama Univ. of Sci., Okayama, Japan
fYear :
1988
fDate :
14-17 Nov 1988
Firstpage :
1029
Abstract :
The applications of a template-matching method for handprinted Japanese kanji character recognition are discussed. Various clustering methods for the intracategory clustering to make the optimal multiple templates are examined. The efficiencies of each method with handprinted kanji characters, using the ratio of variances, are evaluated, and a character recognition experiment are executed with the multiple templates made by the best clustering method
Keywords :
character recognition; handprinted Japanese kanji character recognition; intracategory clustering; multidictionary template matching; variances; Appraisal; Artificial intelligence; Character recognition; Cities and towns; Clustering algorithms; Clustering methods; Dictionaries; Loss measurement; Merging; Pattern matching;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 1988., 9th International Conference on
Conference_Location :
Rome
Print_ISBN :
0-8186-0878-1
Type :
conf
DOI :
10.1109/ICPR.1988.28431
Filename :
28431
Link To Document :
بازگشت