Fuzzy and crisp handwritten character recognition using neural networks

Paul Gader, Magdi Mohamed, Jung Hsien Chiang

Research output: Contribution to conferencePaper

5 Citations (Scopus)

Abstract

In this paper, we describe a neural-network-based handwritten alphabetic character recognition system. Feature vectors are generated using a two-pass algorithm to generate direction magnitude images followed by summing over overlapping zones. Crisp neural networks and fuzzy neural networks are trained using back-propagation. In the crisp case, the desired output is high for the correct class and low for all others. In the fuzzy case, the desired outputs are set using a fuzzy k-nearest neighbor algorithm.

Original languageEnglish
Pages421-426
Number of pages6
Publication statusPublished - 1992 Dec 1
EventProceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 - St.Louis, MO, USA
Duration: 1992 Nov 151992 Nov 18

Other

OtherProceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92
CitySt.Louis, MO, USA
Period92-11-1592-11-18

All Science Journal Classification (ASJC) codes

  • Software

Fingerprint Dive into the research topics of 'Fuzzy and crisp handwritten character recognition using neural networks'. Together they form a unique fingerprint.

  • Cite this

    Gader, P., Mohamed, M., & Chiang, J. H. (1992). Fuzzy and crisp handwritten character recognition using neural networks. 421-426. Paper presented at Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92, St.Louis, MO, USA, .