Feature Subset Selection Using Genetic Algorithms for Handwritten Kannada Alphabets Recognition
Keywords:
Pattern Recognition, OCR, Wavelets Transformation, Kannada alphabets, Genrtic algorithms, Neural NetworksAbstract
The process of pattern recognition pose quiets a lot of challenges especially in recognizing hand-written scripts of different languages in India, in spite of several advancement in technologies pertaining to optical character recognition (OCR). Handwriting continues to persist as means of documenting information for day today life especially in rural areas. There exist a need to develop handwritten character recognition system for its applications in post offices, bank cheque processing, handwritten document processing etc,. In this paper a handwritten Kannada alphabets recognition using neuro-genetic hybrid system is proposed which makes use of wavelet transform coefficients as feature vectors. Subset of these feature vectors is selected using genetic algorithm and is given to neural network for classification. Higher degree of accuracy in results has been obtained with the implementation of this approach on a comprehensive database compared to conventional systems.
References
K V Prema_ and N V Subbareddy- Two-tier architecture for unconstrained handwritten character recognition-SadhanaVol. 27, Part 5, October 2002, pp.585-594.
Hyun-Chul Kim, Daijin Kim, Sung Yang Bang-A numeral character recognition using PCA mixture model, pattern recognition letters, Vol 23, 2002, pp.103-111
G Y Chen, T D Bui, A. Krzyzak-Contour based numeral recognition using mutiwavelets and neural networks, pattern recognition letters, Vol 36, 2003, pp.1597-1604
RejeanPlamondon, Sargur.N.Srihari, On-line and Off-line Handwriting Recognition: A Comprehensive survey, IEEETrans,Pattern Analysis and Machine Intelligence, vol 22, no 1, pp 63-79,Jan 2000
Claus Bahlmann-Directional features in online handwriting recognition, pattern recognition letters, Vol 39, 2006, pp.115-125
Oivind Due Trier, Anil.K.Jain and TorfinnTaxt,-Feature Extraction Methods for Character Recognition – A Surve, July 1995.
Alexander Goltsev, Dmitri Rachkovskij-Combination of the assembly neural network with a perceptron for recognition of handwritten digits arranged in numeral strings, pattern recognition letters, Vol 38, 2005, pp.315-322
Bailing Zhang, Minyue Fu, Hong Yan-A nonlinear neural network model of mixture of local principal component analysis: application to handwritten digits recognition, pattern recognition letters, Vol 34, 2001, pp.203-214
Cheng-Lin Liu, Kazuki Nakashima, Hiroshi Sako, Hiromichi Fujisawa, Handwritten digit recognition: investigation of normalization and feature extraction techniques, Jun 2003
R. JagadeeshKannan and R. Prabhakar- Off-Line Cursive Handwritten Tamil Character Recognition-WSEAS TRANSACTIONS on SIGNAL PROCESSING- ISSN: 1790-5052 Issue 6, Volume 4, June 2008.
G. G. Rajput, RajeswariHorakeri, SidramappaChandrakant- Printed and Handwritten Mixed Kannada Numerals Recognition Using SVM- IJCSE- Vol. 02, No. 05, 2010, 1622-1626
N.Arica and F.T.Yarman_Vural-One dimensional representation of two dimensional information for HMM based handwriting recognition, Pattern recognition letters, vol-21(2000)583-592
Frank Z. Brill, Donald E. Brown and Worthy N.Martin-Fast Genetic Selection of Features for Neural Network Classifiers, IEEE Transaction on neural networks Vol.3, No.2, March-1992.
Seon-Whan Lee-Off-Line Recognition of Totally Unconstrained Handwritten Numerals Using Multilayer Cluster Neural Network, IEEE Transaction on Pattern Analysis and Machine Intelligence Vol.18, No.6, June-1996
Sung-Hyuk Cha, Charles C.Tappert, and Sargur N Srihari-Optimizing Binary Feature Vector Similarity Measure using Genetic Algorithm and Handwritten Character Recognition, Proceedings of ICDAR’03, 0-7695-1960-1/03IEEE.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
