A New Segmentation Algorithm for Online Handwritten Word Recognition in Persian Script

The cursive nature of Persian alphabet, and the complex and convoluted rules regarding this script cause major challenges to segmentation as well as recognition of Persian words. We propose a new segmentation algorithm for the main stroke of online Persian handwritten words. Using this segmentation, we present a perturbation method which is used to generate artificial samples from handwritten words. Our recognition system is composed of three modules. The first module deals with the preprocessing of the data. We propose a wavelet-based smoothing technique which enhances the recognition performance compared to the conventional widely used technique. The second module is word segmentation into convex portions of the global shape which we call Convex Curve Sectors (CCSs). The third module is to analyze those CCSs and use the information for recognition performed by Dynamic Time Warping (DTW) technique. Using CCSs provides the DTW-based classifier with a compact word representation which makes comparison much