A GENERALIZED KNOWLEDGE-BASED SYSTEM FOR THE RECOGNITION OF UNCONSTRAINED HANDWRITTEN NUMERALS

被引：27

作者：

MAI, TA ^{[1
]}

SUEN, CY ^{[1
]}

机构：

[1] CONCORDIA UNIV,DEPT COMP SCI,CTR PATTERN RECOGNIT & MACHINE INTELLIGENCE,MONTREAL H3G 1M8,QUEBEC,CANADA

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS | 1990年 / 20卷 / 04期

基金：

加拿大自然科学与工程研究理事会;

关键词：

D O I：

10.1109/21.105083

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

A method of recognizing unconstrained handwritten numerals using a knowledge base is proposed. Features are collected from a training set and stored in a knowledge base that is used in the recognition stage. Recognition is accomplished by either an inference process or a structural method. The scheme is general, flexible, and applicable to different methods of feature extraction and recognition. By changing the acceptance parameters, a continuous range of performance can be achieved. Encouraging results on nearly 17 000 totally unconstrained handwritten numerals are presented. The performance of the system under different recognition-rejection trade-off ratios is analyzed in detail. © 1990 IEEE

引用

页码：835 / 848

页数：14

共 15 条

[1] AHMED P, 1987, INT J PATTERN RECOGN, V1, P1
[2] BEUN M, 1973, PHILIPS TECH REV, V33, P89
[3] BEUN M, 1973, PHILIPS TECH REV, V33, P130
[4] A COMBINATION OF STATISTICAL AND SYNTACTICAL PATTERN-RECOGNITION APPLIED TO CLASSIFICATION OF UNCONSTRAINED HANDWRITTEN NUMERALS
DUERR, B
HAETTICH, W
TROPF, H
WINKLER, G
[J]. PATTERN RECOGNITION, 1980, 12 (03) : 189 - 199
[5] HULL JJ, 1988, 3RD P USPS ADV TECHN, P1018
[6] KAMANGAR FA, 1988, 3 P US POST SERV ADV, P768
[7] KUAN CL, 1988, 3 P US POST SERV ADV, P1033
[8] STRUCTURAL CLASSIFICATION AND RELAXATION MATCHING OF TOTALLY UNCONSTRAINED HANDWRITTEN ZIP-CODE NUMBERS
LAM, L
SUEN, CY
[J]. PATTERN RECOGNITION, 1988, 21 (01) : 19 - 31
[9] MAI T, 1989, THESIS CONCORDIA U M
[10] METHODOLOGIES IN PATTERN-RECOGNITION AND IMAGE-ANALYSIS - A BRIEF SURVEY
MANTAS, J
[J]. PATTERN RECOGNITION, 1987, 20 (01) : 1 - 6

← 1 2 →