An adaptive line segmentation algorithm (ALSA) for Arabic

Y. S. Elarian, S. A. Mahmoud

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

A technique for the segmentation of document images into lines is presented. The technique computes the needed thresholds from image statistics. Hence, it readily adapts itself to different types of images. The method is tested using 100 images taken from printed, handwritten and historical manuscript categories of text. The results were subjectively evaluated. Its average performance is viewed to be from very good to excellent depending on the category type.

Original languageEnglish
Title of host publicationProceedings of the 2008 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2008
Pages735-739
Number of pages5
StatePublished - 2008

Publication series

NameProceedings of the 2008 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2008

Keywords

  • Arabic text
  • Document analysis
  • Historical manuscript
  • Line segmentation

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint

Dive into the research topics of 'An adaptive line segmentation algorithm (ALSA) for Arabic'. Together they form a unique fingerprint.

Cite this