Handwritten Kannada Vowel Character Recognition Using Crack Codes and Fourier Descriptors

In this paper, we present an efficient method for recognition of basic characters (vowels) of handwritten Kannada text, which is thinning free and independent of size of handwritten characters. Crack codes and Fourier descriptors are used for computing features. The recognition accuracy has been studied by comparing the performances of well known K-NN and SVM classifiers. Five-fold cross validation technique is used for result computation. Experiments are performed on handwritten Kannada vowels consisting of 6500 images with 500 samples for each class. The mean performance of the system with these two shape based features together is 91.24% and 93.73% for K-NN and SVM classifiers, respectively, demonstrating the fact that SVM performs better over K-NN classifier. The system methodology can be extended for the recognition of remaining set of Kannada characters.

[1]  Ashraf S. Mahmoud,et al.  Arabic Character Recognition using Modified Fourier Spectrum (MFS) , 2006, Geometric Modeling and Imaging--New Trends (GMAI'06).

[2]  Tetsushi Wakabayashi,et al.  Handwritten Bangla Compound Character Recognition Using Gradient Feature , 2007 .

[3]  Anilkumar N. Holambe,et al.  Printed and Handwritten Character & Number Recognition of Devanagari Script using Gradient Features , 2010 .

[4]  Fumitaka Kimura,et al.  Recognition of Off-Line Handwritten Devnagari Characters Using Quadratic Classifier , 2006, ICVGIP.

[5]  Masaki Nakagawa,et al.  'Online recognition of Chinese characters: the state-of-the-art , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Neil W. Bergmann,et al.  An Arabic optical character recognition system using recognition-based segmentation , 2001, Pattern Recognit..

[7]  Anil K. Jain,et al.  Feature extraction methods for character recognition-A survey , 1996, Pattern Recognit..

[8]  Malayappan Shridhar,et al.  On Recognition of Handwritten Bangla Characters , 2006, ICVGIP.

[9]  V. Kumar,et al.  FLD Based Unconstrained Handwritten Kannada Character Recognition , 2008, 2008 Second International Conference on Future Generation Communication and Networking Symposia.

[10]  Ashraf S. Mahmoud,et al.  ARABIC CHARACTER RECOGNITION USING MODIFIED FOURIER SPECTRUM (MFS) VS. FOURIER DESCRIPTORS , 2009, Cybern. Syst..

[11]  Tetsushi Wakabayashi,et al.  Handwritten Character Recognition of Popular South Indian Scripts , 2006, SACH.

[12]  Keiji Yamada,et al.  Optimal sampling intervals for Gabor features and printed Japanese character recognition , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[13]  Sargur N. Srihari,et al.  On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[15]  P. Vanaja Ranjan,et al.  Zone based Feature Extraction Algorithm for Handwritten Numeral Recognition of Kannada Script , 2009, 2009 IEEE International Advance Computing Conference.

[16]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[17]  M. Sasikumar,et al.  Feature Analysis for Handwritten Kannada Kagunita Recognition , 2011 .

[18]  G. G. Rajput,et al.  Printed and Handwritten Kannada Numeral Recognition Using Crack Codes and Fourier Descriptors Plate , 2010 .

[19]  Bidyut Baran Chaudhuri,et al.  Indian script character recognition: a survey , 2004, Pattern Recognit..

[20]  Stefan Jäger,et al.  Arabic and Chinese Handwriting Recognition - SACH 2006 Summit College Park, MD, USA, September 27-28, 2006 Selected Papers , 2008, SACH.

[21]  B. V. Dhandra,et al.  Spatial Features for Handwritten Kannada and English Character Recognition , 2010 .

[22]  Jean-Paul Gauthier,et al.  Generalized Fourier Descriptors with Applications to Objects Recognition in SVM Context , 2007, Journal of Mathematical Imaging and Vision.