Title :
Classification of Handwritten Characters by their Symmetry Features
Author :
Holland, Sam ; Neville, Richard
Author_Institution :
Machine Learning & Optimisation Res. Group, Univ. of Manchester, Manchester, UK
Abstract :
We propose a technique to classify characters by two different forms of their symmetry features. The generalized symmetry transform is applied to digits from the USPS data set. These features are then used to train probabilistic neural networks and their performances are compared to the traditional method.
Keywords :
handwritten character recognition; learning (artificial intelligence); neural nets; pattern classification; probability; USPS data set; generalized symmetry transform; handwritten character classification; probabilistic neural networks; Artificial neural networks; Character recognition; Neural networks; Neurons; Optical character recognition software; Optical computing; Optical network units; Probability distribution; Smoothing methods; Testing; character; handwritten; networks; neural; probabilistic; recognition; symmetry;
Conference_Titel :
Advances in Computing, Control, & Telecommunication Technologies, 2009. ACT '09. International Conference on
Conference_Location :
Trivandrum, Kerala
Print_ISBN :
978-1-4244-5321-4
Electronic_ISBN :
978-0-7695-3915-7
DOI :
10.1109/ACT.2009.85
