Effective hyper-spectral image segmentation using multi-scale geometric analysis

O. Levi, S. Cohen, Z. Mhabary

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

2 Scopus citations

Abstract

The wide availability of hyper-spectral (HS) images has fostered the development of new algorithms for remote sensing applications ranging from agricultural and environmental to military use. Nevertheless, the analysis of such voluminous data requires advances analysis and computational methodologies as well as advanced hardware and computational methods. In this paper we introduce a new state of the art method for segmentation of hyper-spectral images. The proposed methodology is based on a multi-scale geometric transformation called the Beamlet Transform. The method is applicable for both mono-spectral and hyper-spectral images where each pixel has its corresponding spectral profile vector. The proposed segmentation method is especially effective when the underlying image consist of relatively large segment with smooth boundaries. In this case it performs exceptional well even in extremely low SNR. The method is unsupervised and assumes no prior knowledge of the image characteristics or features. Furthermore, it involves free parameters which allow fine tuning for a specific application, improving segmentation results. In order to validate the efficiency of our method we used the known Lark algorithm as a benchmark for segmentation of multi-spectral images and show that our new method out-performs the Lark algorithm.

Original languageEnglish
Title of host publicationProc. of the IADIS Int. Conf. - Computer Graphics, Visualization, Computer Vision and Image Processing, CGVCVIP 2010, Visual Commun., VC 2010, Web3DW 2010, Part of the MCCSIS 2010
Pages396-400
Number of pages5
StatePublished - 1 Dec 2010
EventIADIS Int. Conf. - Computer Graphics, Visualization, Computer Vision and Image Processing, CGVCVIP 2010, Visual Commun., VC 2010, Web Virtual Reality and Three-Dimensional Worlds, Web3DW 2010, Part of the MCCSIS 2010 - Freiburg, Germany
Duration: 27 Jul 201029 Jul 2010

Publication series

NameProc. of the IADIS Int. Conf. - Computer Graphics, Visualization, Computer Vision and Image Processing, CGVCVIP 2010, Visual Commun., VC 2010, Web3DW 2010, Part of the MCCSIS 2010

Conference

ConferenceIADIS Int. Conf. - Computer Graphics, Visualization, Computer Vision and Image Processing, CGVCVIP 2010, Visual Commun., VC 2010, Web Virtual Reality and Three-Dimensional Worlds, Web3DW 2010, Part of the MCCSIS 2010
Country/TerritoryGermany
CityFreiburg
Period27/07/1029/07/10

Keywords

  • Beamlet transform
  • Hyper-spectral image
  • Multi-scale geometric analysis
  • Radon transform
  • Segmentation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Information Systems

Fingerprint

Dive into the research topics of 'Effective hyper-spectral image segmentation using multi-scale geometric analysis'. Together they form a unique fingerprint.

Cite this