Neural-network classifiers for recognizing total unconstrained handwritten numerals

Research output: Contribution to journalArticlepeer-review

130 Citations (Scopus)


Artificial neural networks have been recognized as a powerful tool for pattern classification problems, but a number of researchers have also suggested that straightforward neural-network approaches to pattern recognition are largely inadequate for difficult problems such as handwritten numeral recognition. In this paper, we present three sophisticated neural-network classifiers to solve complex pattern recognition problems: multiple multilayer perceptron (MLP) classifier, hidden Markov model (HMM)/MLP hybrid classifier, and structure-adaptive self-organizing map (SOM) classifier. In order to verify the superiority of the proposed classifiers, experiments were performed with the unconstrained handwritten numeral database of Concordia University, Montreal, Canada. The three methods have produced 97.35%, 96.55%, and 96.05% of the recognition rates, respectively, which are better than those of several previous methods reported in the literature on the same database.

Original languageEnglish
Pages (from-to)43-53
Number of pages11
JournalIEEE Transactions on Neural Networks
Issue number1
Publication statusPublished - 1997

Bibliographical note

Funding Information:
Manuscript received January 20, 1996; revised June 19, 1996. This work was supported in part by Grant 961–0901–009–2 from the Korean Science and Engineering Foundation (KOSEF). The author is with the Department of Computer Science, Yonsei University, Seoul 120-749, Korea. Publisher Item Identifier S 1045-9227(97)00239-7.

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence


Dive into the research topics of 'Neural-network classifiers for recognizing total unconstrained handwritten numerals'. Together they form a unique fingerprint.

Cite this