Isan Dhamma Handwritten Characters Recognition System by Using Functional Trees Classifier

In This paper, we present a novel application for the recognition of Isan Dhamma characters. Our algorithm does not require any complicated method and performs word recognition on the whole image holistically, departing from the character based recognition systems of the past. Functional trees (FTs) classifier is the models at the center of this algorithm are trained. The functional trees build univariate decision tree consists of two phases. In the first phase to construct a large decision tree. In the second phase this tree is pruned back. The algorithm to grow the tree follows the standard divide and conquer approach. The local of ten features for Isan Dhamma characters are used. The experiments illustrate the accuracy is 82.33%.