Robust handwritten word recognition with fuzzy sets

Paul Gader, Jung-Hsien Chiang

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

1 Citation (Scopus)

Abstract

A hybrid fuzzy neural system is used to improve a handwritten word recognition algorithm. The word recognition algorithm matches digital images of handwritten words to strings in a lexicon. This algorithm requires a module to assign character class membership values to images of segments of handwritten words. Many of these images are not characters. It is shown that a hybrid neural system consisting of a cascade of a Kohonen Self-Organizing Feature Map (SOFM) followed by Choquet fuzzy integrals can yield improved performance over a multi-layer feedforward network (MLFN). The hybrid method scored a word recognition rate of 85% compared to 77% for the MLFN method.

Original languageEnglish
Title of host publicationProc 3 Int Symp Uncert Model Anal Annu Conf North Amer Fuzzy Inf Process Soc
PublisherIEEE
Pages198-203
Number of pages6
Publication statusPublished - 1995
EventProceedings of the 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society, (ISUMA - NAFIPS'95) - College Park, MD, USA
Duration: 1995 Sep 171995 Sep 20

Other

OtherProceedings of the 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society, (ISUMA - NAFIPS'95)
CityCollege Park, MD, USA
Period95-09-1795-09-20

Fingerprint

Fuzzy sets
Self organizing maps

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Gader, P., & Chiang, J-H. (1995). Robust handwritten word recognition with fuzzy sets. In Proc 3 Int Symp Uncert Model Anal Annu Conf North Amer Fuzzy Inf Process Soc (pp. 198-203). IEEE.
Gader, Paul ; Chiang, Jung-Hsien. / Robust handwritten word recognition with fuzzy sets. Proc 3 Int Symp Uncert Model Anal Annu Conf North Amer Fuzzy Inf Process Soc. IEEE, 1995. pp. 198-203
@inproceedings{f806226b605f48bfae7870cdc3a5068d,
title = "Robust handwritten word recognition with fuzzy sets",
abstract = "A hybrid fuzzy neural system is used to improve a handwritten word recognition algorithm. The word recognition algorithm matches digital images of handwritten words to strings in a lexicon. This algorithm requires a module to assign character class membership values to images of segments of handwritten words. Many of these images are not characters. It is shown that a hybrid neural system consisting of a cascade of a Kohonen Self-Organizing Feature Map (SOFM) followed by Choquet fuzzy integrals can yield improved performance over a multi-layer feedforward network (MLFN). The hybrid method scored a word recognition rate of 85{\%} compared to 77{\%} for the MLFN method.",
author = "Paul Gader and Jung-Hsien Chiang",
year = "1995",
language = "English",
pages = "198--203",
booktitle = "Proc 3 Int Symp Uncert Model Anal Annu Conf North Amer Fuzzy Inf Process Soc",
publisher = "IEEE",

}

Gader, P & Chiang, J-H 1995, Robust handwritten word recognition with fuzzy sets. in Proc 3 Int Symp Uncert Model Anal Annu Conf North Amer Fuzzy Inf Process Soc. IEEE, pp. 198-203, Proceedings of the 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society, (ISUMA - NAFIPS'95), College Park, MD, USA, 95-09-17.

Robust handwritten word recognition with fuzzy sets. / Gader, Paul; Chiang, Jung-Hsien.

Proc 3 Int Symp Uncert Model Anal Annu Conf North Amer Fuzzy Inf Process Soc. IEEE, 1995. p. 198-203.

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

TY - GEN

T1 - Robust handwritten word recognition with fuzzy sets

AU - Gader, Paul

AU - Chiang, Jung-Hsien

PY - 1995

Y1 - 1995

N2 - A hybrid fuzzy neural system is used to improve a handwritten word recognition algorithm. The word recognition algorithm matches digital images of handwritten words to strings in a lexicon. This algorithm requires a module to assign character class membership values to images of segments of handwritten words. Many of these images are not characters. It is shown that a hybrid neural system consisting of a cascade of a Kohonen Self-Organizing Feature Map (SOFM) followed by Choquet fuzzy integrals can yield improved performance over a multi-layer feedforward network (MLFN). The hybrid method scored a word recognition rate of 85% compared to 77% for the MLFN method.

AB - A hybrid fuzzy neural system is used to improve a handwritten word recognition algorithm. The word recognition algorithm matches digital images of handwritten words to strings in a lexicon. This algorithm requires a module to assign character class membership values to images of segments of handwritten words. Many of these images are not characters. It is shown that a hybrid neural system consisting of a cascade of a Kohonen Self-Organizing Feature Map (SOFM) followed by Choquet fuzzy integrals can yield improved performance over a multi-layer feedforward network (MLFN). The hybrid method scored a word recognition rate of 85% compared to 77% for the MLFN method.

UR - http://www.scopus.com/inward/record.url?scp=38449097815&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38449097815&partnerID=8YFLogxK

M3 - Conference contribution

SP - 198

EP - 203

BT - Proc 3 Int Symp Uncert Model Anal Annu Conf North Amer Fuzzy Inf Process Soc

PB - IEEE

ER -

Gader P, Chiang J-H. Robust handwritten word recognition with fuzzy sets. In Proc 3 Int Symp Uncert Model Anal Annu Conf North Amer Fuzzy Inf Process Soc. IEEE. 1995. p. 198-203