Arabic Character Recognition using Artificial Neural Networks and Statistical Analysis

被引：0
|
作者：
Sarhan, Ahmad M. [1 ]
Al Helalat, Omar I. [1 ]
机构：
[1] New York Inst Technol, Abu Dhabi, U Arab Emirates
来源：
PROCEEDINGS OF WORLD ACADEMY OF SCIENCE, ENGINEERING AND TECHNOLOGY, VOL 21 | 2007年 / 21卷
关键词：
ANN; Backpropagation; Gaussian; LMS; MSE; Neuron; standard deviation; Widrow-Hoff rule;
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：
In this paper, an Arabic letter recognition system based on Artificial Neural Networks (ANNs) and statistical analysis for feature extraction is presented. The ANN is trained using the Least Mean Squares (LMS) algorithm. In the proposed system, each typed Arabic letter is represented by a matrix of binary numbers that are used as input to a simple feature extraction system whose output, in addition to the input matrix, are fed to an ANN. Simulation results are provided and show that the proposed system always produces a lower Mean Squared Error (MSE) and higher success rates than the current ANN solutions.
引用
收藏
页码：32 / +
页数：3
相关论文
共 50 条
  • [1] An approach to offline Arabic Character recognition using neural networks
    Nawaz, SN
    Sarfraz, M
    Zidouri, A
    Al-Khatib, WG
    [J]. ICECS 2003: PROCEEDINGS OF THE 2003 10TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS AND SYSTEMS, VOLS 1-3, 2003, : 1328 - 1331
  • [2] Character recognition and its announcing using artificial neural networks
    Rao, MVR
    [J]. JOURNAL OF THE INSTITUTION OF ELECTRONICS AND TELECOMMUNICATION ENGINEERS, 1995, 41 (5-6): : 321 - 323
  • [3] HANDWRITTEN CHARACTER RECOGNITION SYSTEM USING ARTIFICIAL NEURAL NETWORKS
    Gorgel, Pelin
    Oztas, Oguzhan
    [J]. ISTANBUL UNIVERSITY-JOURNAL OF ELECTRICAL AND ELECTRONICS ENGINEERING, 2007, 7 (01): : 309 - 313
  • [4] OPTICAL CHARACTER-RECOGNITION USING ARTIFICIAL NEURAL NETWORKS
    ALPAYDIN, E
    [J]. FIRST IEE INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS, 1989, : 191 - 195
  • [5] Assamese Character Recognition with Artificial Neural Networks
    Aydin, Musa
    Celik, Enes
    [J]. 2013 21ST SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2013,
  • [6] Handwritten Character Recognition with Artificial Neural Networks
    Kouamo, Stephane
    Tangha, Claude
    [J]. DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE, 2012, 151 : 535 - +
  • [7] Multi-lingual character recognition using Artificial Neural Networks
    Meiyappan, SS
    Sridharan, S
    Ososanya, ET
    [J]. PROCEEDINGS OF THE IEEE SOUTHEASTCON '96: BRINGING TOGETHER EDUCATION, SCIENCE AND TECHNOLOGY, 1996, : 417 - 420
  • [8] Arabic Handwritten Character Recognition Based on Convolution Neural Networks
    Bouchriha, Lamia
    Zrigui, Ahmed
    Mansouri, Sadek
    Berchech, Salma
    Omrani, Syrine
    [J]. ADVANCES IN COMPUTATIONAL COLLECTIVE INTELLIGENCE, ICCCI 2022, 2022, 1653 : 286 - 293
  • [9] An Arabic character recognition system using neural network
    Sanossian, HYY
    [J]. NEURAL NETWORKS FOR SIGNAL PROCESSING VI, 1996, : 340 - 348
  • [10] Optimized leaky ReLU for handwritten Arabic character recognition using convolution neural networks
    Bahera H. Nayef
    Siti Norul Huda Sheikh Abdullah
    Rossilawati Sulaiman
    Zaid Abdi Alkareem Alyasseri
    [J]. Multimedia Tools and Applications, 2022, 81 : 2065 - 2094
12345