Gujarati Handwritten Character Recognition Using Hybrid Method Based On Binary Tree-Classifier And K-Nearest Neighbour

Gujarati is a language used by more than 50 million people worldwide. Due to dissemination of ICT in India need for Optical Character Recognition (OCR) activities for Indian script is in demand. One can obtain very less OCR related research work for Gujarati script, especially for handwritten form. This paper describes a hybrid approach based on tree classifier and k-Nearest Neighbor (k-NN) for recognition of handwritten Gujarati characters. Combination of structural features and statistical features is used for classification and identification of characters. The features are relatively simple to derive. The structural features are selected by studying the appearance of various handwritten characters. The moment based and centroid based features are first time combined for character recognition of Gujarati script. A success rate of 63% is achieved using proposed method, which is acceptable, as it is one of the few attempts to recognize whole character set of Gujarati handwritten characters. KeywordsFeature representation, k-Nearest Neighbor, Moments, Optical Character Recognition (OCR), Treeclassifier

[1]  Apurva Desai.  Handwritten Gujarati Numeral Optical Character Recognition using Hybrid Feature Extraction Technique , 2010, IPCV.

[2]  Bidyut Baran Chaudhuri,et al.  Automatic recognition of printed Oriya script , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[3]  Bidyut Baran Chaudhuri,et al.  A Hybrid Scheme for Handprinted Numeral Recognition Based on a Self-Organizing Network and MLP Classifiers , 2002, Int. J. Pattern Recognit. Artif. Intell..

[4]  Chandan Singh,et al.  A Gurmukhi script recognition system , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[5]  N. V. Subba Reddy,et al.  Multilevel Classifiers in Recognition of Handwritten Kannada Numerals , 2008 .

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

[7]  Sanghamitra Mohanty,et al.  Performance Comparison of SVM and K-NN for Oriya Character Recognition , 2011 .

[8]  U. Pal,et al.  Segmentation of Bangla unconstrained handwritten text , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[9]  Anilkumar N. Holambe,et al.  Printed and Handwritten Character &Number Recognition of Devanagari Script using SVM and KNN , 2010 .

[10]  S.V. Rajashekararadhya,et al.  Neural network based handwritten numeral recognition of Kannada and Telugu scripts , 2008, TENCON 2008 - 2008 IEEE Region 10 Conference.

[11]  Atul Negi,et al.  Zone identification in the printed Gujarati text , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[12]  Cheng-Lin Liu,et al.  Handwritten digit recognition: benchmarking of state-of-the-art techniques , 2003, Pattern Recognit..

[13]  Santanu Chaudhury,et al.  Bengali alpha-numeric character recognition using curvature features , 1993, Pattern Recognit..

[14]  Bidyut Baran Chaudhuri,et al.  A complete printed Bangla OCR system , 1998, Pattern Recognit..

[15]  Fumitaka Kimura,et al.  Oriya handwritten numeral recognition system , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[16]  Bidyut Baran Chaudhuri,et al.  An OCR system to read two Indian language scripts: Bangla and Devnagari (Hindi) , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[17]  Apurva A. Desai,et al.  Gujarati handwritten numeral optical character reorganization through neural network , 2010, Pattern Recognit..

[18]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

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

[20]  Chandan Singh,et al.  A Complete OCR System for Gurmukhi Script , 2002, SSPR/SPR.

[21]  Richard J. Prokop,et al.  A survey of moment-based techniques for unoccluded object representation and recognition , 1992, CVGIP Graph. Model. Image Process..