Title :
A new method of distortion-invariant character recognition
Author :
Menu, Eric ; Lefrere, L. ; Lecourtier, Yves
Author_Institution :
LTIS, Saint-Quentin-en-Yvelines, France
fDate :
30 Aug-3 Sep 1992
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;
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
DOI :
10.1109/ICPR.1992.201849
