Skip to main content
Presentation
Chain-based extraction of line segments to describe images
Faculty of Informatics - Papers (Archive)
  • A. Chalechale, University of Wollongong
  • G. Naghdy, University of Wollongong
  • Prashan Premaratne, University of Wollongong
  • H. Moghaddasi, National Iranian Oil Company, Tehran
RIS ID
11212
Publication Date
27-6-2004
Publication Details

This article was originally published as: Chalechale, A, Naghdy, G, Pramaratne, P & Moghaddasi, H, Chain-based extraction of line segments to describe images, 2004 IEEE International Conference on Multimedia and Expo(ICME '04), 27-30 June 2004, 1, 355-358. Copyright IEEE 2004.

Abstract

This work presents a novel fast method for line segment extraction, based on a chain code representation of edge maps. It has a parallel nature and can be employed on parallel machines. In the first phase it breaks the macro chains into several micro chains after applying shifting, smoothing and differentiating. The micro chains are then approximated by straight line segments. In the second phase, based on the length and the error criteria, the line segments are grouped into much longer lines. The experimental results show a significant improvement in the number of line segments extracted while their accumulative length keeps high.

Citation Information
A. Chalechale, G. Naghdy, Prashan Premaratne and H. Moghaddasi. "Chain-based extraction of line segments to describe images" (2004)
Available at: http://works.bepress.com/pdissanayakemudiyanselage/19/