International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 149 - Number 3 |
Year of Publication: 2016 |
Authors: Sandeep Kaur, Rekha Bhatia |
![]() |
Sandeep Kaur, Rekha Bhatia . Gurmukhi Printed Character Recognition using Hierarchical Centroid Method and SVM. International Journal of Computer Applications. 149, 3 ( Sep 2016), 24-27. DOI=10.5120/ijca2016911367
In this paper the system for the recognition of printed Gurmukhi character is proposed. Hierarchical centroid method is used for extracting the feature from images of printed characters. The main advantage of using this method is that it gives size invariant feature vector and therefore can play important role for manuscript recognition. The dataset used in this study consists of 29 different font styles of the printed characters. The classification is done by using Support Vector Machine. The performance of the classifier is determined by measuring accuracy using 10-fold cross validation procedure. The highest accuracy obtained on SVM is 97.87% with the combination of nu-SVC type and RBF kernel.