DocumentCode
3059634
Title
A new method of distortion-invariant character recognition
Author
Menu, Eric ; Lefrere, L. ; Lecourtier, Yves
Author_Institution
LTIS, Saint-Quentin-en-Yvelines, France
fYear
1992
fDate
30 Aug-3 Sep 1992
Firstpage
599
Lastpage
602
Abstract
As part of the wide-ranging subject of optical character recognition, the authors present a new set of primitives and their utilization in a modular neural network for distortion-invariant character recognition. An application using topographical survey maps is also described
Keywords
neural nets; optical character recognition; distortion-invariant character recognition; modular neural network; topographical survey maps; Character recognition; Gravity; Laboratories; Neural networks; Optical character recognition software; Optical computing; Optical distortion; Optical fiber networks; Shape; Technical drawing;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on
Conference_Location
The Hague
Print_ISBN
0-8186-2915-0
Type
conf
DOI
10.1109/ICPR.1992.201849
Filename
201849
Link To Document