IMPROVED HANDWRITTEN CHARACTER-RECOGNITION USING 2ND-ORDER INFORMATION FROM TRAINING SET

被引：3

作者：

KOVACS, ZM ^{[1
]}

ROVATTI, R ^{[1
]}

GUERRIERI, R ^{[1
]}

RAGAZZONI, R ^{[1
]}

机构：

[1] UNIV MODENA,FAC INGN,I-41100 MODENA,ITALY

来源：

ELECTRONICS LETTERS | 1993年 / 29卷 / 14期

关键词：

PATTERN RECOGNITION; CHARACTER RECOGNITION;

D O I：

10.1049/el:19930873

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The problem of improving the capability of statistical character classifiers based on finite and sparse training sets is addressed. A significant improvement is obtained coupling standard classifiers based on the k-nearest neighbours technique with a second higher level classification stage. This method has been applied to three existing classifiers reducing the error rate at zero rejection of approximately 17%.

引用

页码：1308 / 1310

页数：3

共 6 条

[1] FUKUNAGA K, 1990, INTRO STATISTICAL PA
[2] GARRIS MD, 1992, NIST SPECIAL DATABAS
[3] COMPUTER RECOGNITION OF HAND-WRITTEN CHARACTERS USING THE DISTANCE TRANSFORM
KOVACS, ZM
GUERRIERI, R
[J]. ELECTRONICS LETTERS, 1992, 28 (19) : 1825 - 1827
[4] A CLASS OF NEW KNN METHODS FOR LOW SAMPLE PROBLEMS
PARTHASARATHY, G
CHATTERJI, BN
[J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1990, 20 (03): : 715 - 718
[5] AN INFORMATION THEORETIC APPROACH TO RULE INDUCTION FROM DATABASES
SMYTH, P
GOODMAN, RM
[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 1992, 4 (04) : 301 - 316
[6] Takahashi H., 1991, P INT C DOCUMENT ANA, P821

← 1 →