文章基本信息

标题：ArabicandUrdu Text Segmentation ChallengesandTechniques
本地全文：下载
作者：Atif Mahmood
期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2013
卷号：4
期号：1
页码：32-34
语种：English
出版社：Ayushmaan Technologies
摘要：Text Segmentation is one of the critical and vital step in OCR system of any language because accuracy of OCR depends upon correctly segmented characters. Segmentation divide the text images into its constituent parts (i.e. lines, components or words and individual characters). As Urdu and Arabic are highly cursive and context sensitive in nature and have improper space between words therefore, segmentation is hard as compared to other languages like English, Hindi, Chinese, etc. This paper presents a survey of techniques regarding text segmentation of Urdu and Arabic languages and also discusses various challenges in segmentation.
关键词：Segmentation;Challenges;Projection profile;Pixel Count; Labelling;Clustering