DocumentCode
2766576
Title
Korean character recognition using neural networks
Author
Koh, J. ; Moon, G.S. ; Mehrotra, K.G. ; Mohan, C.K. ; Ranka, S.
Author_Institution
Syracuse Univ., NY, USA
fYear
1990
fDate
8-10 Oct 1990
Firstpage
162
Lastpage
165
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
Keywords
character recognition; computerised pattern recognition; neural nets; Hough transform inputs; Korean character recognition; backpropagation algorithm; neural networks; printed Korean characters; Character recognition; Computational Intelligence Society; Data preprocessing; Image segmentation; Moon; Neural networks; Neurons; Pixel; Shape; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Frontiers of Massively Parallel Computation, 1990. Proceedings., 3rd Symposium on the
Conference_Location
College Park, MD
Print_ISBN
0-8186-2053-6
Type
conf
DOI
10.1109/FMPC.1990.89454
Filename
89454
Link To Document