Title :
Transformation of optimized prototypes for handwritten digit recognition
Author_Institution :
Dept. of Electr. Eng., Sydney Univ., NSW, Australia
Abstract :
Proposes a method for handwritten digit recognition using optimized prototypes generated through learning and transformation. In this method a set of prototypes are obtained from training samples and mapped to a multi-layer neural network for optimization to improve their classification power. The new prototypes are then transformed geometrically to produce a larger set of prototypes for recognition of testing samples. The method has been verified to work well in experimental studies
Keywords :
image classification; learning (artificial intelligence); multilayer perceptrons; optical character recognition; optimisation; classification power; handwritten digit recognition; learning; multilayer neural network; optimized prototypes; training; transformation; Deformable models; Handwriting recognition; Multi-layer neural network; Neural networks; Optimization methods; Prototypes; Robustness; Testing; Training data; Writing;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7803-1775-0
DOI :
10.1109/ICASSP.1994.389578
