Efficient recognition of Odiya numerals using low complexity neural classifier

Author

Majhi, Babita ; Satpathy, Jeetamitra ; Rout, Minakhi

Author_Institution

Dept. of IT, Siksha O Anusandhan Univ., Bhubaneswar, India

fYear

2011

fDate

28-30 Dec. 2011

Firstpage

1

Lastpage

4

Abstract

The paper develops an efficient but simple adaptive nonlinear classifier for recognition of handwritten Odiya numerals. The standard gradient and curvature features are extracted and nonlinearly mapped by sine/cosine expansions. These nonlinear inputs are fed to a low complexity classifier. The simulation results show excellent classification accuracy when test features are used.

Keywords

computational complexity; gradient methods; handwritten character recognition; image classification; neural nets; adaptive nonlinear classifier; curvature features; gradient features; handwritten Odiya numeral recognition; low complexity classifier; low complexity neural classifier; sine-cosine expansions; Accuracy; Educational institutions; Feature extraction; Handwriting recognition; Hidden Markov models; Training; Vectors; Character recognition; artificial neural network; curvature feature; gradient feature; handwritten odiya numerals recognition; principal component analysis and neural network;

fLanguage

English

Publisher

ieee

Conference_Titel

Energy, Automation, and Signal (ICEAS), 2011 International Conference on

Conference_Location

Bhubaneswar, Odisha

Print_ISBN

978-1-4673-0137-4

Type

conf

DOI

10.1109/ICEAS.2011.6147094

Filename

6147094