Cursive character recognition by learning vector quantization

被引：31

作者：

Camastra, F

Vinciarelli, A

机构：

[1] Epsag Spa, I-16154 Genoa, Italy

[2] IDIAP, Inst Dalle Molle Intelligence Artif Percept, CH-1920 Martigny, Switzerland

来源：

PATTERN RECOGNITION LETTERS | 2001年 / 22卷 / 6-7期

关键词：

cursive character recognition; feature extraction; cross-validation; learning vector quantization;

D O I：

10.1016/S0167-8655(01)00008-3

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a cursive character recognizer embedded in an off-line cursive script recognition system. The recognizer is composed of two modules: the first one is a feature extractor, the second one a learning vector quantizer. The selected feature set was compared to Zernike polynomials using the same classifier. Experiments are reported on a database of about 49,000 isolated characters. (C) 2001 Elsevier Science B.V. All rights reserved.

引用

页码：625 / 629

页数：5