Title :
A new fuzzy geometric representation for online isolated character recognition
Author :
Hebert, Jean-Francois ; Parizeau, Marc ; Ghazzali, Nadia
Author_Institution :
Comput. Vision & Syst. Lab., Laval Univ., Que., Canada
Abstract :
Introduces a fuzzy representation for isolated character description. This representation maps a character from its original sequence of 2D coordinates into a fuzzy vector space that can thereafter serve as input to any artificial neural network classifier. Recognition experiments on isolated digits extracted from the UNIPEN database are their conducted to evaluate the performances of the proposed representation using a hybrid Kohonen-perceptron (KP) neural network
Keywords :
fuzzy set theory; geometry; handwritten character recognition; perceptrons; self-organising feature maps; sequences; 2D coordinates; UNIPEN database; fuzzy geometric representation; fuzzy vector space; hybrid Kohonen-perceptron neural network; isolated digits; online isolated character recognition; Artificial neural networks; Character recognition; Computer vision; Fuzzy sets; Handwriting recognition; Laboratories; Mathematics; Neural networks; Read only memory; Statistics;
Conference_Titel :
Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-8186-8512-3
DOI :
10.1109/ICPR.1998.711891
