Title :
Permutative coding technique for handwritten digit recognition system
Author :
Kussul, E. ; Baidyk, T.
Author_Institution :
Center of Appl. Sci. & Technol. Dev., UNAM, Mexico City, Mexico
Abstract :
The new neural classifier for the handwritten digit recognition is proposed. The classifier is based on the Permutative Coding technique. This coding technique is derived from the associative-projective neural networks developed in the 80th-90th. The classifier performance was tested on the MNIST database. The error rate of 0.54% was obtained.
Keywords :
encoding; feature extraction; handwritten character recognition; neural nets; MNIST database; associative-projective neural networks; encoding; feature extraction; handwritten digit recognition system; neural classifier; permutative coding technique; Brightness; Convolution; Error analysis; Feature extraction; Handwriting recognition; Image databases; Neural networks; Shape; Spatial databases; System testing;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1223743
