A solution for line segmentation problems in sindhi character recognition system

Abstract

The Sindhi language uses extended and modified set of the Arabic and Persian alphabets. It is the largest extension of the Arabic alphabet. Thus, Arabic or any other Arabic script based language character recognition system cannot recognize all characters of Sindhi. From character recognition point of view, Sindhi is a tough script. Sindhi’s cursive, context-sensitive characteristics, a large set of characters, highly similar shapes of the basic character, font-type variations, and size variations create high challenges for Sindhi character recognition research. In addition, line segmentation is a hard task as we have non-uniformity in the line heights. In this paper, we present an algorithm for segmenting the Sindhi text image into lines. The proposed algorithm solves the over-segmentation and under-segmentation problems in the line segmentation for Sindhi documents. The algorithm is tested on 100 text images of different Sindhi books and it has successfully segmented 99.95% lines correctly.