MACHINE RECOGNITION OF OPTICALLY CAPTURED MACHINE PRINTED ARABIC TEXT

被引：28

作者：

ELKHALY, F ^{[1
]}

SIDAHMED, MA ^{[1
]}

机构：

[1] UNIV WINDSOR,DEPT ELECT ENGN,WINDSOR N9B 3P4,ONTARIO,CANADA

来源：

PATTERN RECOGNITION | 1990年 / 23卷 / 11期

关键词：

Arabic text; Moments; Optically captured; Separation; Thinning; Thresholding;

D O I：

10.1016/0031-3203(90)90116-3

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 discusses the development of algorithms for the machine recognition of optically captured Arabic characters and their isolation from the printed text. Arabic text is formed from a set of connected or individual fonts. Recognition algorithms based only on individual characters need to be supplemented with a separation algorithm. Moment-invariant descriptors are investigated for the purpose of recognition of individual characters. Meanwhile, to recognize connected machine printed characters, an algorithm for separation of individual characters is developed. © 1990.

引用

页码：1207 / 1214

页数：8

共 14 条

[1] ALMALLIN H, 1987, IEEE T SMC, V9
[2] BADRELDIN A, 1985, THESIS U WINDSOR
[3] Chottera A., 1982, Canadian Electrical Engineering Journal, V7, P29
[4] Duda R. O., 1973, PATTERN CLASSIFICATI, V3
[5] A RECOGNITION ALGORITHM FOR HANDPRINTED ARABIC NUMERALS
GOLSHAN, N
HSU, CC
[J]. IEEE TRANSACTIONS ON SYSTEMS SCIENCE AND CYBERNETICS, 1970, SSC6 (03): : 246 - &
[6] Gonzalez R. C., 1977, DIGITAL IMAGE PROCES
[7] GRANLUND GH, 1972, IEEE T COMPUT C, V21, P198
[8] VISUAL-PATTERN RECOGNITION BY MOMENT INVARIANTS
HU, M
[J]. IRE TRANSACTIONS ON INFORMATION THEORY, 1962, 8 (02): : 179 - &
[9] ONLINE RECOGNITION OF HAND-WRITTEN CHARACTERS UTILIZING POSITIONAL AND STROKE VECTOR SEQUENCES
IKEDA, K
YAMAMURA, T
MITAMURA, Y
FUJIWARA, S
TOMINAGA, Y
KIYONO, T
[J]. PATTERN RECOGNITION, 1981, 13 (03) : 191 - 206
[10] KOHAN S, 1987, IEEE T, P274

← 1 2 →