Handwritten character recognition based on hybrid neural networks

被引：0
|
作者：
Wang, P [1 ]
Sun, GM [1 ]
Zhang, XM [1 ]
机构：
[1] Beijing Polytech Univ, Dept Elect Engn, Beijing, Peoples R China
来源：
NEURAL NETWORK AND DISTRIBUTED PROCESSING | 2001年 / 4555卷
关键词：
character recognition; neural network;
D O I：
10.1117/12.441669
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A hybrid neural network system for the recognition of handwritten character using SOFM,BP and Fuzzy network is presented. The horizontal and vertical project of preprocessed character and 4_directional edge project are used as feature vectors. In order to improve the recognition effect, the GAT algorithm is applied. Through the hybrid neural network system, the recognition rate is improved visibly.
引用
收藏
页码：65 / 70
页数：6
相关论文
共 50 条
  • [1] Hybrid optimization of feedforward neural networks for handwritten character recognition
    Utschick, W
    Nossek, JA
    1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V: VOL I: PLENARY, EXPERT SUMMARIES, SPECIAL, AUDIO, UNDERWATER ACOUSTICS, VLSI; VOL II: SPEECH PROCESSING; VOL III: SPEECH PROCESSING, DIGITAL SIGNAL PROCESSING; VOL IV: MULTIDIMENSIONAL SIGNAL PROCESSING, NEURAL NETWORKS - VOL V: STATISTICAL SIGNAL AND ARRAY PROCESSING, APPLICATIONS, 1997, : 147 - 150
  • [2] Arabic Handwritten Character Recognition Based on Convolution Neural Networks
    Research Laboratory in Algebra, Numbers Theory and Intelligent Systems RLANTIS, Monastir University, Monastir, Tunisia
    不详
    不详
    94140, France
    Commun. Comput. Info. Sci., 2022, (286-293):
  • [3] Arabic Handwritten Character Recognition Based on Convolution Neural Networks
    Bouchriha, Lamia
    Zrigui, Ahmed
    Mansouri, Sadek
    Berchech, Salma
    Omrani, Syrine
    ADVANCES IN COMPUTATIONAL COLLECTIVE INTELLIGENCE, ICCCI 2022, 2022, 1653 : 286 - 293
  • [4] Handwritten Character Recognition with Artificial Neural Networks
    Kouamo, Stephane
    Tangha, Claude
    DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE, 2012, 151 : 535 - +
  • [5] On-line handwritten character recognition by a hybrid method based on neural networks and pattern matching
    Cho, JW
    Lee, SY
    Park, CH
    FROM NATURAL TO ARTIFICIAL NEURAL COMPUTATION, 1995, 930 : 926 - 933
  • [6] Deep Neural Networks for Handwritten Chinese Character Recognition
    Maidana, Renan G.
    Monteiro, Juarez
    Granada, Roger
    Amory, Alexandre M.
    Barros, Rodrigo C.
    2017 6TH BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS), 2017, : 192 - 197
  • [7] Handwritten Sindhi Character Recognition Using Neural Networks
    Awan, Shafique Ahmed
    Hussainabro, Zahid
    Jalbani, Akhtar Hussain
    Hakro, Dil Nawaz
    Hameed, Maryam
    MEHRAN UNIVERSITY RESEARCH JOURNAL OF ENGINEERING AND TECHNOLOGY, 2018, 37 (01) : 191 - 196
  • [8] Handwritten word recognition with character and inter-character neural networks
    Gader, PD
    Mohamed, M
    Chiang, JH
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1997, 27 (01): : 158 - 164
  • [9] Pattern fusion in feature recognition neural networks for handwritten character recognition
    Lee, SJ
    Tsai, HL
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1998, 28 (04): : 612 - 617
  • [10] Multilinguistic handwritten character recognition by Bayesian decision-based neural networks
    Fu, HC
    Xu, YY
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1998, 46 (10) : 2781 - 2789
12345