A three-dimensional neural network model for unconstrained handwritten numeral recognition: A new approach

被引：0

作者：

Reddy, NVS ^{[1
]}

Nagabhushan, P ^{[1
]}

机构：

[1] SJ Coll Engn, Dept Comp Sci & Engn, Mysore 570006, Karnataka, India

来源：

PATTERN RECOGNITION | 1998年 / 31卷 / 05期

关键词：

feature extraction; modified self-organizing map; learning vector quantization; 3-D neural network; conflict resolution;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The paper describes a three-dimensional (3-D) neural network recognition system for conflict resolution in recognition of unconstrained handwritten numerals. This neural network classifier is a combination of modified self-organizing map (MSOM) and learning vector quantization (LVQ). The 3-D neural network recognition system has many layers of such neural network classifiers and the number of layers forms the third dimension. The Experiments are conducted employing SOM, MSOM, SOM and LVQ, and MSOM and LVQ networks. These experiments on a database of unconstrained handwritten samples show that the combination of MSOM and LVQ performs better than other networks in terms of classification, recognition and training time. The 3-D neural network eliminates the substitution error. (C) 1998 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

引用

页码：511 / 516

页数：6

共 50 条

[41] Numeral recognition using a multi neural network model
Inooka, Y
Fukumi, M
Akamatsu, N
[J]. ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3, 1998, : 1094 - 1097
[42] The application of convolution neural networks in handwritten numeral recognition
College of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao, China
[J]. Int. J. Database Theory Appl., 3 (367-376):
[43] Unconstrained handwritten numeral recognition using fuzzy rule-based classifier
Fang, X
Alouani, AT
[J]. PROCEEDINGS OF THE THIRTY-FOURTH SOUTHEASTERN SYMPOSIUM ON SYSTEM THEORY, 2002, : 256 - 260
[44] A new artificial neural network based approach for recognition of handwritten digits
Agrawal, Anil Kumar
Yadav, Susheel
Gupta, Amit Ambar
Pandey, Vishnu
[J]. INTERNATIONAL JOURNAL OF APPLIED PATTERN RECOGNITION, 2023, 7 (02) : 100 - 121
[45] Research on handwritten numeral recognition method based on improved genetic algorithm and neural network
Yan, Tai-Shan
Tao, Yong-Qing
Cui, Du-Wu
[J]. 2007 INTERNATIONAL CONFERENCE ON WAVELET ANALYSIS AND PATTERN RECOGNITION, VOLS 1-4, PROCEEDINGS, 2007, : 1271 - 1276
[46] Handwritten numeral string recognition using neural network classifier trained with negative data
Kim, HY
Lim, KT
Nam, YS
[J]. EIGHTH INTERNATIONAL WORKSHOP ON FRONTIERS IN HANDWRITING RECOGNITION: PROCEEDINGS, 2002, : 395 - 400
[47] Combination of the assembly neural network with a perceptron for recognition of handwritten digits arranged in numeral strings
Goltsev, A
Rachkovskij, D
[J]. PATTERN RECOGNITION, 2005, 38 (03) : 315 - 322
[48] A current mode VLSI neural fuzzy classifier for unconstrained handwritten numeral classification
Li, GX
Shi, BX
[J]. ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3, 1998, : 562 - 565
[49] Recognition of unconstrained handwritten numerals by a radial basis function neural network classifier
Hwang, YS
Bang, SY
[J]. PATTERN RECOGNITION LETTERS, 1997, 18 (07) : 657 - 664
[50] Three-dimensional site characterisation: neural network approach
Juang, CH
Jiang, T
Christopher, RA
[J]. GEOTECHNIQUE, 2001, 51 (09): : 799 - 809

← 1 2 3 4 5 →