ABSTRACT

In this manuscript handwritten Gurmukhi character recognition for isolated characters is proposed. We have used some statistical features like zonal density, projection histograms (horizontal, vertical and both diagonal), distance profiles (from left, right, top and bottom sides). In addition, we have used background directional distribution (BDD) features. Our database consists of 200 samples of each of basic 35 characters of Gurmukhi script collected from different writers. These samples are pre-processed and normalized to 32*32 sizes. SVM, K-NN and PNN classifiers are used for classification. The performance comparison of features used in different combination with different classifiers is presented and analysed. The highest accuracy obtained is 95.04% as 5-fold cross validation of whole database using zonal density and background distribution features in combination with SVM classifier used with RBF kernel.