Automatic Processing of Handwritten Arabic Forms Using Neural Networks

被引:0
作者
Asiri, A. [1 ]
Khorsheed, M. S. [1 ]
机构
[1] King Saud Univ, Coll Comp & Informat, Dept Comp Engn, Riyadh 11543, Saudi Arabia
来源
PROCEEDINGS OF WORLD ACADEMY OF SCIENCE, ENGINEERING AND TECHNOLOGY, VOL 7 | 2005年 / 7卷
关键词
Neural Networks; Pattern Recognition; Image Processing and Understanding; Arabic OCR;
D O I
暂无
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Among the vast range of off-line optical character recognition applications is the machine processing of forms. The objective is to imitate the human ability to read but at higher speed. This paper presents a neural network based system to recognise handwritten Arabic characters collected from more than 500 forms. Wavelet coefficients extracted from the character samples are used to tune the neural network weights. The performance of the system is assessed using a corpus that includes 15800 character samples.
引用
收藏
页码:313 / 317
页数:5
相关论文
共 9 条
[1]  
BOUSLAMA F, 1996, P N AM FUZZ INF PROC, P142
[2]  
Hassibi K, 1994, 4 INT C EXH MULT COM
[3]   Off line Arabic character recognition - A review [J].
Khorsheed, MS .
PATTERN ANALYSIS AND APPLICATIONS, 2002, 5 (01) :31-45
[4]  
MOSFEQ R, 1996, 5 INT C EXH MULT COM
[5]  
Mowlaei A, 2002, DSP 2002: 14TH INTERNATIONAL CONFERENCE ON DIGITAL SIGNAL PROCESSING PROCEEDINGS, VOLS 1 AND 2, P923, DOI 10.1109/ICDSP.2002.1028240
[6]  
Pao Y. H., 1989, ADAPTIVE PATTERN REC
[7]  
Said F. N., 1999, P 5 INT C DOC AN REC
[8]   An Arabic character recognition system using neural network [J].
Sanossian, HYY .
NEURAL NETWORKS FOR SIGNAL PROCESSING VI, 1996, :340-348
[9]  
[No title captured]