Handwritten Numeral Recognition Based on Modular Neural Networks Utilizing Rotated and Translated Images 


Vol. 7,  No. 6, pp. 1834-1843, Jun.  2000
10.3745/KIPSTE.2000.7.6.1834


PDF
  Abstract

In this paper, we propose a modular neural network based classification method for handwritten numerals utilizing rotated and translated images of an input image. The whole numeral pattern space is divided into smaller spaces which overlap each other and form multiple clusters. On these multiple clusters, multiple multilayer perceptrons (MLP) neural networks, specialized in those clusters, are constructed. Thus, each MLP acts as an expert network on the corresponding cluster. An MLP is also used as a gating network functioning as a mediator among the multiple MLPs. In the learning phase, an input numeral image is dithered by tow geometric operations of translation and rotation so that new numeral images similar to original one are generated. In the recognition phase, we utilize not only input numeral image, but also nearly generated images through the rotation and the translation of the original image. Thus, multiple output values for those generated images were combined to make class decision by various combination methods. The experimental results confirm the validity of the proposed method.

  Statistics
  Cite this article

[IEEE Style]

K. T. Lim, Y. S. Nam, S. I. Chien, "Handwritten Numeral Recognition Based on Modular Neural Networks Utilizing Rotated and Translated Images," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 7, no. 6, pp. 1834-1843, 2000. DOI: 10.3745/KIPSTE.2000.7.6.1834.

[ACM Style]

Kil Taek Lim, Yun Seok Nam, and Sung Il Chien. 2000. Handwritten Numeral Recognition Based on Modular Neural Networks Utilizing Rotated and Translated Images. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 7, 6, (2000), 1834-1843. DOI: 10.3745/KIPSTE.2000.7.6.1834.

Forms

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

Old Journals

Indexing

All publications of TKIPS is indexed in DOI, EBSCO, Google Scholar, Crossref, and CrossCheck.

TKIPS is also selected as the Journal for Accreditation by NRF (National Research Foundation of Korea).

Related Journals