The Modified ART1 Network using Multiresolution Mergence: Mixed Character Recognition


The KIPS Transactions:PartB , Vol. 14, No. 3, pp. 215-222, Jun. 2007
10.3745/KIPSTB.2007.14.3.215,   PDF Download:

Abstract

As Information Technology growing, the character recognition application plays an important role in the ubiquitous environment. In this paper, we propose the Modified ART1 network using Multiresolution Mergence to the problems of the character recognition. The approach is based on the unsupervised neural network and multiresolution. In order to decrease noises and to increase the classification rate of the characters, we propose the mutiresolution mergence strategy using both high resolution and low resolution information. Also, to maximize the effect of mutiresolution mergence, we use a modified ART1 method with a different similarity measure. Our experimental results show that the classification rate of character is quite increased as well as the performance of the propose algorithm in conjunction with the similarity measure is improved comparing to the conventional ART1 algorithm in this application.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
G. H. Choi and M. J. Kim, "The Modified ART1 Network using Multiresolution Mergence: Mixed Character Recognition," The KIPS Transactions:PartB , vol. 14, no. 3, pp. 215-222, 2007. DOI: 10.3745/KIPSTB.2007.14.3.215.

[ACM Style]
Gyung Hyun Choi and Min Je Kim. 2007. The Modified ART1 Network using Multiresolution Mergence: Mixed Character Recognition. The KIPS Transactions:PartB , 14, 3, (2007), 215-222. DOI: 10.3745/KIPSTB.2007.14.3.215.