Korean character recognition using neural networks

J. Koh, G. S. Moon, K. G. Mehrotra, C. K. Mohan, S. Ranka

Research output: Chapter in Book/Entry/PoemConference contribution

1 Scopus citations

Abstract

A neural network approach for recognizing printed Korean characters, based on a variant of the backpropagation algorithm, is presented. Implementation of the algorithms for neural networks with Hough transform inputs provided excellent recognition: about 81% of the training samples and 73% of the tested samples can be recognized.

Original languageEnglish (US)
Title of host publicationProc 3 Symp Front Massively Parallel Comput Frontiers 90
PublisherIEEE Computer Society
Pages162-165
Number of pages4
ISBN (Print)0818620536
StatePublished - 1990
EventProceedings of the 3rd Symposium on the Frontiers of Massively Parallel Computation - Frontiers '90 - College Park, MD, USA
Duration: Oct 8 1990Oct 10 1990

Publication series

NameProc 3 Symp Front Massively Parallel Comput Frontiers 90

Other

OtherProceedings of the 3rd Symposium on the Frontiers of Massively Parallel Computation - Frontiers '90
CityCollege Park, MD, USA
Period10/8/9010/10/90

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Korean character recognition using neural networks'. Together they form a unique fingerprint.

Cite this