A Novel Approach to Segmentation of Persian Cursive Script Using Decision Tree

Abstract

In this paper, we propose a novel method for segmentation of online Persian handwriting into the fundamental building blocks of Persian letters. Employing the findings of our previous work to determine the segmentation points of cursive words and applying some smoothing techniques to improve our results, we have advanced our model to form the pre-segments into the predefined building blocks (BBs) which will be used later for recognizing letters in written words. We have utilized a decision tree to accomplish this task and the 98.6% accuracy has been obtained in forming the BBs as the overall result.