Title :
Off-line recognition of totally unconstrained handwritten numerals using multilayer cluster neural network
Author :
Lee, Seong-Whan ; Kim, Young Joon
Author_Institution :
Dept. of Comput. Sci., Chungbuk Nat. Univ., Cheongju, South Korea
Abstract :
In this paper, we propose a simple multilayer cluster neural network with five independent subnetworks for off-line recognition of totally unconstrained handwritten numerals. We also show that the use of genetic algorithms for avoiding the problem of finding local minima in training the multilayer cluster neural network with gradient descent technique reduces error rates
Keywords :
optical character recognition; error rate reduction; genetic algorithms; gradient descent technique; local minima; multilayer cluster neural network; off-line recognition; totally unconstrained handwritten numerals; Character recognition; Detectors; Feature extraction; Genetic algorithms; Handwriting recognition; Image coding; Image edge detection; Multi-layer neural network; Neural networks; Nonhomogeneous media;
Conference_Titel :
Pattern Recognition, 1994. Vol. 2 - Conference B: Computer Vision & Image Processing., Proceedings of the 12th IAPR International. Conference on
Conference_Location :
Jerusalem
Print_ISBN :
0-8186-6270-0
DOI :
10.1109/ICPR.1994.576997
