A diffusion approach to unsupervised segmentation of hyper-spectral images

Alon Schclar*, Amir Averbuch

*Corresponding author for this work

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


Hyper-spectral cameras capture images at hundreds and even thousands of wavelengths. These hyper-spectral images offer orders of magnitude more intensity information than RGB images. This information can be utilized to obtain segmentation results which are superior to those that are obtained using RGB images. However, many of the wavelengths are correlated and many others are noisy. Consequently, the hyper-spectral data must be preprocessed prior to the application of any segmentation algorithm. Such preprocessing must remove the noise and inter-wavelength correlations and due to complexity constraints represent each pixel by a small number of features which capture the structure of the image. The contribution of this paper is three-fold. First, we utilize the diffusion bases dimensionality reduction algorithm (Schclar and Averbuch in Diffusion bases dimensionality reduction, pp. 151–156, [1]) to derive the features which are needed for the segmentation. Second, we describe a faster version of the diffusion bases algorithm which uses symmetric matrices. Third, we propose a simple algorithm for the segmentation of the dimensionality reduced image. Successful application of the algorithms to hyper-spectral microscopic images and remote-sensed hyper-spectral images demonstrate the effectiveness of the proposed algorithms.

Original languageEnglish
Title of host publicationComputational Intelligence - 9th International Joint Conference, IJCCI 2017, Revised Selected Papers
EditorsKurosh Madani, Juan Julian Merelo, Kevin Warwick, Christophe Sabourin, Kevin Warwick
PublisherSpringer Verlag
Number of pages16
ISBN (Print)9783030164683
StatePublished - 2019
Event9th International Joint Conference on Computational Intelligence, IJCCI 2017 - Funchal, Madeira, Portugal
Duration: 1 Nov 20173 Nov 2017

Publication series

NameStudies in Computational Intelligence
ISSN (Print)1860-949X


Conference9th International Joint Conference on Computational Intelligence, IJCCI 2017
CityFunchal, Madeira


  • Diffusion bases
  • Dimensionality reduction
  • Hyper-spectral sensing
  • Segmentation


Dive into the research topics of 'A diffusion approach to unsupervised segmentation of hyper-spectral images'. Together they form a unique fingerprint.

Cite this