ICA Mixture Model for Unsupervised Classification of non-Gaussian Classes in Multi/Hyperspectral Imagery

C. A. Shah, M. K. Arora, Pramod Kumar Varshney

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

Conventional remote sensing classification techniques model the data in each class with a multivariate Gaussian distribution. Inadequacy of such algorithms stems from Gaussian distribution assumption for the class-component densities, which is only an assumption rather than a demonstrable property of natural spectral classes. In this paper, we present an Independent Component Analysis (ICA) based approach for unsupervised classification of multi/hyperspectral imagery. ICA employed for a mixture model, estimates the data density in each class and models class distributions with non-Gaussian structure (i.e. leptokurtic or platykurtic p.d.f), formulating the ICA mixture model (ICAMM). It finds independent components and the mixing matrix for each class, using the extended information-maximization learning algorithm, and computes the class membership probabilities for each pixel. We apply the ICAMM for unsupervised classification of images from a multispectral sensor - Positive Systems Multi-Spectral Imager, and a hyperspectral sensor - Airborne Visible/Infrared Imaging Spectrometer (AVIRIS). Four feature extraction techniques: Principal Component Analysis, Segmented Principal Component Analysis, Orthogonal Subspace Projection and Projection Pursuit have been considered as a preprocessing step to reduce dimensionality of the hyperspectral data. The results demonstrate that the ICAMM significantly outperforms the K-means algorithm for land cover classification of remotely sensed images.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsS.S. Shen, P.E. Lewis
Pages569-580
Number of pages12
Volume5093
DOIs
StatePublished - 2003
EventAlgorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery IX - Orlando, FL, United States
Duration: Apr 21 2003Apr 24 2003

Other

OtherAlgorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery IX
CountryUnited States
CityOrlando, FL
Period4/21/034/24/03

    Fingerprint

Keywords

  • Blind source separation (BSS)
  • ICA mixture model (ICAMM)
  • Independent component analysis (ICA)
  • Multispectral and hyperspectral imagery
  • Unsupervised classification
  • Unsupervised feature extraction

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Shah, C. A., Arora, M. K., & Varshney, P. K. (2003). ICA Mixture Model for Unsupervised Classification of non-Gaussian Classes in Multi/Hyperspectral Imagery. In S. S. Shen, & P. E. Lewis (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (Vol. 5093, pp. 569-580) https://doi.org/10.1117/12.486382