Line Image Classification by NG×SOM: Application to Handwritten Character Recognition

Authors:
Makoto Otani;Kouichi Gunya;Tetsuo Furukawa
Affiliations:
Kyushu Institute of Technology, Kitakyushu, Japan 808-0196;Kyushu Institute of Technology, Kitakyushu, Japan 808-0196;Kyushu Institute of Technology, Kitakyushu, Japan 808-0196
Venue:
WSOM '09 Proceedings of the 7th International Workshop on Advances in Self-Organizing Maps
Year:
2009

Citing 6
Cited 0

Shape approximation of arc patterns using dynamic neural networks

Signal Processing
Skeletons from dot patterns: a neural network approach

Pattern Recognition Letters
Batch and median neural gas

Neural Networks - 2006 Special issue: Advances in self-organizing maps--WSOM'05
Shape recovery by a generalized topology preserving SOM

Neurocomputing
SOM of SOMs

Neural Networks
SOM of SOMs: self-organizing map which maps a group of self-organizing maps

ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

A method for generating a self-organizing map of line images is proposed. In the proposed method, called the NG×SOM, a set of data distributions is represented by a product space organized by a set of neural gas networks (NGs) and a self-organizing map (SOM). In this paper, it is assumed that the line images dealt with by the NG×SOM have the same, yet unknown, topology. Thus the task of the NG×SOM is to generate a map of line images with the same topology, in which the images are continuously and naturally morphed from one into another. We applied the NG×SOM to a handwritten character recognition task. The results obtained show that this method is effective, particularly when the number of training data is small.