Performance analysis of different classifiers for recognition of handwritten Gurmukhi characters using hybrid features

The paper is focuses on using hybridization of multiple features with different classifiers for the purpose of recognition of isolated handwritten Gurmukhi character images. We have tested four different types of features named as Histogram Oriented Gradient (HOG), Distance Profile, Background Directional Distribution (BDD) and Zonal Based Diagonal (ZBD). HOG feature is computed by information of Directions provided from gradient's tangent of arc. Distance Profile can be computed by counting pixels from bounding line of image of character to edge of character from different directions. BDD feature can be computed by background distribution of foreground pixels to background pixels in eight different directions. For computation of ZBD feature, image is segmented into 100 equal zones then feature is calculated from pixels of each zone by traveling along its diagonal direction. For these experiment seven thousand isolated images of Gurmukhi characters have been tested. The experiment achieves a maximum recognition accuracy of 97.257% with 5-fold and 97.671% with 10-fold cross validation by applying hybrid features on SVM classifier.

[1]  B. N. Chatterji.  Feature Extraction Methods for Character Recognition , 1986 .

[2]  V. A. Gaikwad.  An Overview of Character Recognition Focused On Off- line Handwriting , 2008 .

[3]  Gurpreet Singh Lehal.  A Complete Machine-Printed Gurmukhi OCR System , 2009 .

[4]  Dharam Veer Sharma,et al.  Recognition of Isolated Handwritten Characters in Gurmukhi Script , 2010 .

[5]  Ankush Mittal,et al.  Evaluation of Different Feature Extractors and Classifiers for Offline Handwritten Devnagari Character Recognition , 2011 .

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

[7]  Roman Yampolskiy,et al.  Feature Extraction Methods for Character Recognition , 2004 .

[8]  Munish Kumar,et al.  Classification of characters and grading writers in offline handwritten Gurmukhi script , 2011, 2011 International Conference on Image Information Processing.

[9]  Chandan Singh,et al.  A post-processor for Gurmukhi OCR , 2002 .

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

[11]  Nafiz Arica,et al.  An overview of character recognition focused on off-line handwriting , 2001, IEEE Trans. Syst. Man Cybern. Syst..

[12]  S. Himavathi,et al.  Diagonal Feature Extraction Based Handwritten Character System Using Neural Network , 2010 .

[13]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[14]  Rajesh Kumar,et al.  Online Handwritten Gurmukhi Character Recognition Using Elastic Matching , 2008, 2008 Congress on Image and Signal Processing.

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

[16]  K. Siddharth,et al.  Handwritten Gurmukhi Character Recognition Using Statistical and Background Directional Distribution Features , 2011 .

[17]  Dharam Veer Sharma,et al.  Recognition of Isolated Handwritten Characters of Gurumukhi Script using Neocognitron , 2010 .

[18]  Flávio Bortolozzi,et al.  Foreground and background information in an HMM-based method for recognition of isolated characters and numeral strings , 2004, Ninth International Workshop on Frontiers in Handwriting Recognition.

[19]  Anuj Sharma,et al.  Online Handwritten Gurmukhi Character Recognition , 2009 .

[20]  Renu Dhir,et al.  Use of Gabor Filters for Recognition of Handwritten Gurmukhi Character , 2012 .