Analytical Study of Various Feature Extraction Techniques for Offline Handwritten Gurmukhi Character RecognitionAuthor : Anupam Garg, Manish Kumar Jindal and Amanpreet Singh
Volume 8 No.2 April-June 2019 pp 90-93
This paper focus on the approach which is based on the combination of various feature extraction techniques. The proposed approach can manifest the classification process if the focus is on the statistical features which are extracted from individual offline handwritten Gurmukhi characters. The five types of feature extraction techniques which are engrossed in this work are, namely, diagonal features, parabola curve fitting based features; power curve fitting based features; vertically peak extent based features; and horizontally peak extent based features. For the classification, we have considered RBF-SVM classifier. Experimentation work is conducted on 7000 samples of isolated offline handwritten Gurmukhi characters with 5-fold cross validation technique. Principal component analysis is applied to providing the recognition accuracy of 94.6% when compared with state-of-the-art techniques.
Character Recognition, Feature Extraction, Classification, SVM
 A. Aggarwal, R. Rani, and R. Dhir, “Handwritten Devanagari Character Recognition Using Gradient Features,” International Journal of Advanced Research in Computer Science and Software Engineering, Vol. 2, No. 5, pp. 85-90, 2012.
 R. Joshi and G. Agnihotri, “Recognition of Gurmukhi character style through Neural Networks,” International Journal of Scientific Engineering and Applied Science, Vol. 1, No. 9, pp. 435-439, 2015.
 M. Kumar, R. K. Sharma and M. K. Jindal, “k -Nearest Neighbour Based Offline handwritten Gurmukhi Character Recognition,” Proceedings of International Conference on Image Information Processing, pp. 1-4, 2011.
 M. Kumar, R. K. Sharma and M. K. Jindal, “SVM based offline handwritten Gurmukhi character recognition,” Proceedings of the International Workshop on Soft Computing and Knowledge Discovery (SCAKD), Vol. 758, pp. 51- 62, 2011.
 M. Kumar, R. K. Sharma and M. K. Jindal, “Offline handwritten Gurmukhi character recognition: Study of different feature-classifier combinations,” Proceedings of the Workshop on Document Analysis and Recognition, pp. 94–99, 2012.
 M. Kumar, M. K. Jindal and R. K. Sharma, “PCA Based Offline Handwritten Gurmukhi Character Recognition System,” Smart Computing Review, Vol. 3, No. 5, pp. 346-357, 2013.
 M. Kumar, R. K. Sharma and M. K. Jindal, “A Novel Feature Extraction Technique for Offline Handwritten Gurmukhi Character Recognition,” IETE Journal of Research, Vol. 59, No. 6, pp. 687-692, 2013.
 G. S. Lehal and C. Singh, “Feature extraction and classification for OCR of Gurmukhi script,” Vivek, Vol. 12, No. 2, pp. 2-12, 1999.
 A. Purohit and S. S. Chauhan, “A Literature Survey on Handwritten Character Recognition,” International Journal of Computer Science and Information Technologies, pp. 1-5, 2016.
 S. Rani and G. S. Lehal, “Recognition Based Classification of Gurmukhi Manuscripts,” IEEE Symposium on Colossal Data Analysis and Networking (CDAN), pp. 1-5, 2016.
 D. V. Sharma and P. Jhajj, “Recognition of isolated handwritten characters in Gurmukhi script,” International Journal of Computer Applications, Vol. 4, No. 8, pp. 9-17, 2010.
 M. Kumar, R. K. Sharma and M. K. Jindal, “A Novel Hierarchical Technique for Offline Handwritten Gurumukhi Character Recognition,” National Academy Science Letters, Vol. 37, No. 6, pp. 567-572, 2014.
 M. Kumar, M. K. Jindal and R. K. Sharma, “Efficient Feature Extraction Techniques for Offline Handwritten Gurmukhi Character Recognition,” National Academy of Sciences, Vol. 37, No. 4, pp. 381–391, 2014.