Publication

Text-Line Segmentation of Large Titles and Headings in Arabic Like Script

Riaz Ahmad, M. Zeshan Afzal, S. Faisal Rashid, Marcus Liwicki, Andreas Dengel

In: 2017 1st International Workshop on Arabic Script Analysis and Recognition - Workshop Booklet. IEEE International Workshop on Arabic Script Analysis and Recognition (ASAR-2017) April 3-5 Nancy France Pages 168-172 IEEE Xplore 2017.

Abstract

Current approaches for text line segmentation often are either very specialized to specific domains or they depend on many parameters. More specifically, the extraction of text-lines with large sizes, i.e.,headings and titles int he Arabic like script could not be segmented correctly by state-of-the-art methods. In this work, we present a simple and robust text-line segmentation approach. The proposed method is tested on real Pashto scanned images and it outperforms a recent text independent state of the art method with respect to performance and time

Weitere Links

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz