A new type of recurrent neural network for handwritten character recognition

Seong Whan Lee, Young Jaon Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

In this paper, we propose a new type of recurrent neural network for handwritten character recognition. The proposed recurrent neural network differs from Jordan and Elman recurrent neural networks in mew of functions and architectures because it was originally extended from the multilayer feedforward neural network for improving discrimination and generalization power in recognizing handwritten characters. We also analyze the performance of the proposed recurrent neural network by performing recognition experiments with the totally unconstrained handwritten numeral database of Concordia University of Canada. The experimental results showed that the proposed recurrent neural network greatly improves the discrimination and generalization power.

Original languageEnglish
Title of host publicationProceedings of the 3rd International Conference on Document Analysis and Recognition, ICDAR 1995
PublisherIEEE Computer Society
Pages38-41
Number of pages4
ISBN (Electronic)0818671289
DOIs
Publication statusPublished - 1995 Jan 1
Event3rd International Conference on Document Analysis and Recognition, ICDAR 1995 - Montreal, Canada
Duration: 1995 Aug 141995 Aug 16

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR
Volume1
ISSN (Print)1520-5363

Conference

Conference3rd International Conference on Document Analysis and Recognition, ICDAR 1995
CountryCanada
CityMontreal
Period95/8/1495/8/16

Fingerprint

Character recognition
Recurrent neural networks
Feedforward neural networks
Multilayer neural networks
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Lee, S. W., & Kim, Y. J. (1995). A new type of recurrent neural network for handwritten character recognition. In Proceedings of the 3rd International Conference on Document Analysis and Recognition, ICDAR 1995 (pp. 38-41). [598939] (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR; Vol. 1). IEEE Computer Society. https://doi.org/10.1109/ICDAR.1995.598939

A new type of recurrent neural network for handwritten character recognition. / Lee, Seong Whan; Kim, Young Jaon.

Proceedings of the 3rd International Conference on Document Analysis and Recognition, ICDAR 1995. IEEE Computer Society, 1995. p. 38-41 598939 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, SW & Kim, YJ 1995, A new type of recurrent neural network for handwritten character recognition. in Proceedings of the 3rd International Conference on Document Analysis and Recognition, ICDAR 1995., 598939, Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, vol. 1, IEEE Computer Society, pp. 38-41, 3rd International Conference on Document Analysis and Recognition, ICDAR 1995, Montreal, Canada, 95/8/14. https://doi.org/10.1109/ICDAR.1995.598939
Lee SW, Kim YJ. A new type of recurrent neural network for handwritten character recognition. In Proceedings of the 3rd International Conference on Document Analysis and Recognition, ICDAR 1995. IEEE Computer Society. 1995. p. 38-41. 598939. (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR). https://doi.org/10.1109/ICDAR.1995.598939
Lee, Seong Whan ; Kim, Young Jaon. / A new type of recurrent neural network for handwritten character recognition. Proceedings of the 3rd International Conference on Document Analysis and Recognition, ICDAR 1995. IEEE Computer Society, 1995. pp. 38-41 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR).
@inproceedings{e4da676365f14ee18be2930ff868322e,
title = "A new type of recurrent neural network for handwritten character recognition",
abstract = "In this paper, we propose a new type of recurrent neural network for handwritten character recognition. The proposed recurrent neural network differs from Jordan and Elman recurrent neural networks in mew of functions and architectures because it was originally extended from the multilayer feedforward neural network for improving discrimination and generalization power in recognizing handwritten characters. We also analyze the performance of the proposed recurrent neural network by performing recognition experiments with the totally unconstrained handwritten numeral database of Concordia University of Canada. The experimental results showed that the proposed recurrent neural network greatly improves the discrimination and generalization power.",
author = "Lee, {Seong Whan} and Kim, {Young Jaon}",
year = "1995",
month = "1",
day = "1",
doi = "10.1109/ICDAR.1995.598939",
language = "English",
series = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",
publisher = "IEEE Computer Society",
pages = "38--41",
booktitle = "Proceedings of the 3rd International Conference on Document Analysis and Recognition, ICDAR 1995",

}

TY - GEN

T1 - A new type of recurrent neural network for handwritten character recognition

AU - Lee, Seong Whan

AU - Kim, Young Jaon

PY - 1995/1/1

Y1 - 1995/1/1

N2 - In this paper, we propose a new type of recurrent neural network for handwritten character recognition. The proposed recurrent neural network differs from Jordan and Elman recurrent neural networks in mew of functions and architectures because it was originally extended from the multilayer feedforward neural network for improving discrimination and generalization power in recognizing handwritten characters. We also analyze the performance of the proposed recurrent neural network by performing recognition experiments with the totally unconstrained handwritten numeral database of Concordia University of Canada. The experimental results showed that the proposed recurrent neural network greatly improves the discrimination and generalization power.

AB - In this paper, we propose a new type of recurrent neural network for handwritten character recognition. The proposed recurrent neural network differs from Jordan and Elman recurrent neural networks in mew of functions and architectures because it was originally extended from the multilayer feedforward neural network for improving discrimination and generalization power in recognizing handwritten characters. We also analyze the performance of the proposed recurrent neural network by performing recognition experiments with the totally unconstrained handwritten numeral database of Concordia University of Canada. The experimental results showed that the proposed recurrent neural network greatly improves the discrimination and generalization power.

UR - http://www.scopus.com/inward/record.url?scp=85004175700&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85004175700&partnerID=8YFLogxK

U2 - 10.1109/ICDAR.1995.598939

DO - 10.1109/ICDAR.1995.598939

M3 - Conference contribution

AN - SCOPUS:85004175700

T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

SP - 38

EP - 41

BT - Proceedings of the 3rd International Conference on Document Analysis and Recognition, ICDAR 1995

PB - IEEE Computer Society

ER -