A method for the segmentation of connected handwritten Persian digits

Abstract

This article presents in two modules a new method for segmenting connected handwritten Persian digits using the characteristics of the foreground and utilizing the background skeleton.The first module excavates all the valleys and hills , if there are any ,from the upper pixels and lower pixels of the thinned image respectively. Then feature point excavate. For better segmentation the digits , a separability degree is calculated, regarding the height of the hills and valleys close to each feature point considering the characteristic of connected Persian digits. Then the significance degree is calculated to determine of its influence rate in segmentation. Then, using that, one or few points with high significance degree, which are more influence in the segmentation, are selected as the cutting points.Having excavated the background skeleton, the second module begins to identify the priority points in the skeleton in order to connect them to the cutting points The conducted experiments confirm the accuracy of the factors utilized and the results indicates a correct segmentation at a rate of 97.2%.