Offline Handwritten Gurmukhi Character Recognition Using Combination of k-NN and SVM ClassifiersAuthor : Anupam Garg, Manish Kumar Jindal and Amanpreet Singh
Volume 8 No.2 April-June 2019 pp 111-115
In this paper, we have presented a technique for recognition of offline handwritten segmented Gurmukhi characters using combinations of feature extraction techniques and classification techniques. Principal Component Analysis (PCA) is used to find efficient features which have further been used in the classification process. For classification, k-NN and SVM are considered in this paper. SVM is considered in three different kernels, namely, linear-SVM, polynomial-SVM and RBF-SVM, which can also be considered to improve recognition accuracy. For experimental results, we have collected 8960 samples of offline handwritten Gurmukhi characters. The dataset partitioning strategy and k-fold cross validation technique are used for selecting the training and testing dataset. We have achieved a recognition accuracy of 92.3%, using the combination of linear-SVM, polynomial-SVM and k-NN classifiers. In this case, we have taken 80% data as training dataset and the remaining data as testing dataset.
Handwritten Character Recognition, Feature Extraction, Classification, Feature Selection, PCA, k-NN, SVM
 V. Deepu, S. Madhvanath, and A. G. Ramakrishnan, “Principal Component Analysis for online handwritten character recognition,”17th International Conference on Pattern Recognition (ICPR), Vol. 2, pp. 327-330, 2004.
 S. Sundaram and A. G. Ramakrishnan, “Two Dimensional Principal Component Analysis for Online Tamil Character Recognition,” 11th International Conference Frontiers in Handwriting Recognition (ICFHR), pp. 88-94, 2008.
 V. N. M. Aradhya and G. H. Kumar, and S. Noushath, “Multilingual OCR system for south Indian scripts and English documents: An approach based on Fourier transform and principal component
analysis,” Engineering Applications of Artificial Intelligence, Vol. 21, pp. 658-668, 2008.
 A. Sharma, R. Kumar, and R. K. Sharma, “Online handwritten Gurmukhi character recognition using elastic matching,” International Journal of Congress on Image and Signal Processing (IJCISP), Vol. 2, pp. 391-396, 2008.
 B. Singh, A. Mittal, and D. Ghosh, “An Evaluation of Different feature extractors and classifiers for offline handwritten Devanagri character recognition,” Journal of Pattern Recognition Research, Vol. 2, pp. 269-277, 2011.
 M. Kumar, M. K. Jindal and R. K. Sharma, “SVM based offline handwritten Gurmukhi character recognition,” International Workshop on Soft Computing and Knowledge Discovery, Vol. 758, pp. 51-62, 2011.
 U. Bhattacharya, M. Shridhar, S. K. Parui, P. K. Sen and B. B. Chaudhuri, “Offline recognition of handwritten Bangla characters: an efficient two-stage approach,” Pattern Analysis and Applications, Vol. 15, No. 4, pp. 445-458, 2012.
 M. Kumar, M. K. Jindal and R. K. Sharma, “k-NN based offline handwritten Gurmukhi character recognition,” International Conference on Information and Image Processing, Shimla, pp. 1-4, 2011.
 M. Kumar, M. K. Jindal and R. K. Sharma, “Classification of Characters and Grading Writers in Offline Handwritten Gurmukhi Script,” International Conference on Information and Image Processing, Shimla, pp. 1-4, 2011.
 M. Kumar, M. K. Jindal and R. K. Sharma, “Offline Handwritten Gurmukhi Character Recognition: Study of different features and classifiers combinations,” Workshop on Document Analysis and Recognition, pp. 94-99, 2012.
 S. Basu, N. Das, R. Sarkar, M. Kundu, M. Nasipuri, D. K. Basu, “A hierarchical approach to recognition of handwritten Bangla characters,” Pattern Recognition, Vol. 42, No. 7, pp. 1467-1484, 2009.
 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.
 M. Kumar, R. K. Sharma and M. K. Jindal, “MDP Feature Extraction Technique for Offline Handwritten Gurmukhi Character Recognition,” Smart Computing Review, Vol. 3, No. 6, pp. 397-404, 2013.