Adaptive dissection based subword segmentation of printed Arabic text

Abstract

Numerous segmentation and recognition techniques have been proposed in literature for Arabic OCR system. Correct and efficient segmentation of Arabic text into characters is considered to be a fundamental problem. While OCR systems for other languages do not need segmentation for printed text for successful recognition, it is essential to design robust and powerful segmentation algorithms or employ segmentation free recognition schemes for printed Arabic text. Even more, in recognition of handwritten characters, segmentation is considered to be indispensable. Most of current segmentation technique suffers from over segmentation and under segmentation in addition to not being adaptive in nature. In this paper, we have proposed a new sub-word segmentation scheme, which is independent of font size and font type.