Conference paper · 2004

On the Choice of Training Set, Architecture and Combination Rule of Multiple MLP Classifiers for Multiresolution Recognition of Handwritten Characters

Ujjwal Bhattacharya, Szilárd Vajda, A. Mallick, B.B. Chaudhuri, Abdel Belaïd

International Workshop on Frontiers in Handwriting Recognition (IWFHR), 419–424 · Published 23 December 2004 · DOI 10.1109/iwfhr.2004.77

View at the publisherCite this paper

In brief

“On the Choice of Training Set, Architecture and Combination Rule of Multiple MLP Classifiers for Multiresolution Recognition of Handwritten Characters” is a 2004 conference paper by Ujjwal Bhattacharya and 4 co-authors, published in International Workshop on Frontiers in Handwriting Recognition (IWFHR). OpenAlex counts 25 citations as of 16 November 2026. The publisher's version is not open access, and OpenAlex records no free legal copy.

Citations
25
Most cited in
2012 (3)
Field-weighted impact
2.27
References
22
Authors
5

Abstract

A script independent recognition scheme for handwritten characters using multiple MLP classifiers and wavelet transform-based multiresolution pixel features is presented. We studied four different approaches for combination of multiple MLP classifiers and observed that a weighted majority voting approach provided the best recognition performance. Also, a thumb rule for the selection of network architecture has… Read the full abstract at the publisher.

Excerpt. This paper is not open access.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Bhattacharya, U., Vajda, S., Mallick, A., Chaudhuri, B., & Belaïd, A. (2004). On the Choice of Training Set, Architecture and Combination Rule of Multiple MLP Classifiers for Multiresolution Recognition of Handwritten Characters. International Workshop on Frontiers in Handwriting Recognition (IWFHR), 419–424. https://doi.org/10.1109/iwfhr.2004.77

MLA 9

Bhattacharya, Ujjwal, et al. “On the Choice of Training Set, Architecture and Combination Rule of Multiple MLP Classifiers for Multiresolution Recognition of Handwritten Characters.” International Workshop on Frontiers in Handwriting Recognition (IWFHR), 2004, pp. 419–424. https://doi.org/10.1109/iwfhr.2004.77.

Chicago

Bhattacharya, Ujjwal, Szilárd Vajda, A. Mallick, B.B. Chaudhuri, and Abdel Belaïd. 2004. “On the Choice of Training Set, Architecture and Combination Rule of Multiple MLP Classifiers for Multiresolution Recognition of Handwritten Characters.” International Workshop on Frontiers in Handwriting Recognition (IWFHR): 419–424. https://doi.org/10.1109/iwfhr.2004.77.

Harvard

Bhattacharya, U. et al. (2004) ‘On the Choice of Training Set, Architecture and Combination Rule of Multiple MLP Classifiers for Multiresolution Recognition of Handwritten Characters’, International Workshop on Frontiers in Handwriting Recognition (IWFHR), pp. 419–424. doi:10.1109/iwfhr.2004.77.

IEEE

U. Bhattacharya, S. Vajda, A. Mallick, B. Chaudhuri, and A. Belaïd, “On the Choice of Training Set, Architecture and Combination Rule of Multiple MLP Classifiers for Multiresolution Recognition of Handwritten Characters,” International Workshop on Frontiers in Handwriting Recognition (IWFHR), pp. 419–424, 2004, doi: 10.1109/iwfhr.2004.77.

BibTeX

@inproceedings{bhattacharya2004choice,
  title     = {{On the Choice of Training Set, Architecture and Combination Rule of Multiple MLP Classifiers for Multiresolution Recognition of Handwritten Characters}},
  author    = {Bhattacharya, Ujjwal and Vajda, Szilárd and Mallick, A. and Chaudhuri, B.B. and Belaïd, Abdel},
  booktitle = {International Workshop on Frontiers in Handwriting Recognition (IWFHR)},
  year      = {2004},
  pages     = {419--424},
  doi       = {10.1109/iwfhr.2004.77},
  url       = {https://doi.org/10.1109/iwfhr.2004.77}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201233
201311
201422
201511
201611
201711
201811

Its field-weighted citation impact is 2.27: it has been cited 2.27 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Handwritten Text Recognition Techniques

  • handwritten character recognition
  • classifier combination
  • weighted majority voting
  • training data selection
  • network architecture selection
  • wavelet features
  • handwritten digits

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Bhattacharya, U., Vajda, S., Mallick, A., Chaudhuri, B., & Belaïd, A. (2004). On the Choice of Training Set, Architecture and Combination Rule of Multiple MLP Classifiers for Multiresolution Recognition of Handwritten Characters. International Workshop on Frontiers in Handwriting Recognition (IWFHR), 419–424. https://doi.org/10.1109/iwfhr.2004.77

How many times has this paper been cited?

25 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

OpenAlex records no free legal copy. Check your library's access, the authors' pages or a repository, or ask the corresponding author for a copy.

Who wrote this paper?

Ujjwal Bhattacharya, Szilárd Vajda, A. Mallick, B.B. Chaudhuri, Abdel Belaïd.

What is the DOI of this paper?

10.1109/iwfhr.2004.77. The permanent link is https://doi.org/10.1109/iwfhr.2004.77.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.