DocumentCode :
1527407
Title :
Handwritten digit recognition by adaptive-subspace self-organizing map (ASSOM)
Author :
Zhang, Bailing ; Fu, Minyue ; Yan, Hong ; Jabri, Marwan A.
Author_Institution :
Dept. of Electr. & Comput. Eng., Newcastle Univ., NSW, Australia
Volume :
10
Issue :
4
fYear :
1999
fDate :
7/1/1999 12:00:00 AM
Firstpage :
939
Lastpage :
945
Abstract :
The adaptive-subspace self-organizing map (ASSOM) proposed by Kohonen is a recent development in self-organizing map (SOM) computation. In this paper, we propose a method to realize ASSOM using a neural learning algorithm in nonlinear autoencoder networks. Our method has the advantage of numerical stability. We have applied our ASSOM model to build a modular classification system for handwritten digit recognition. Ten ASSOM modules are used to capture different features in the ten classes of digits. When a test digit is presented to all the modules, each module provides a reconstructed pattern and the system outputs a class label by comparing the ten reconstruction errors. Our experiments show promising results. For relatively small size modules, the classification accuracy reaches 99.3% on the training set and over 97% on the testing set
Keywords :
handwritten character recognition; image coding; learning (artificial intelligence); numerical stability; principal component analysis; self-organising feature maps; ASSOM; SOM; adaptive-subspace self-organizing map; handwritten digit recognition; modular classification system; neural learning algorithm; nonlinear autoencoder networks; numerical stability; Data structures; Handwriting recognition; Learning systems; Neural networks; Nonhomogeneous media; Numerical stability; Pattern recognition; Principal component analysis; System testing; Vectors;
fLanguage :
English
Journal_Title :
Neural Networks, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9227
Type :
jour
DOI :
10.1109/72.774267
Filename :
774267
Link To Document :
بازگشت