Issues in segmenting hyperspectral imagery from histograms

J. Silverman, S. R. Rotman, K. L. Duseau, C. E. Caefer

Research output: Contribution to journalConference articlepeer-review

2 Scopus citations


In earlier work, we have shown that starting with the first two or three principal component images, one could form a two or three-dimensional histogram and cluster all pixels on the basis of the proximity to the peaks of the histogram. Here, we discuss two major issues which arise in all classification/segmentation algorithms. The first issue concerns the desired range of segmentation levels. We explore this issue by means of plots of histogram peaks versus the scaling parameter used to map into integer bins. By taking into account the role of P min the minimum definition of a peak in the histogram, we demonstrate the viability of this approach. The second issue is that of devising a merit function for assessing segmentation quality. Our approach is based on statistical tests used in the Automatic Classification of Time Series (ACTS) algorithm and is shown to support and be consistent with the histogram plots.

Original languageEnglish
Pages (from-to)41-51
Number of pages11
JournalProceedings of SPIE - The International Society for Optical Engineering
StatePublished - 3 May 2004
EventImaging Spectrometry IX - San Diego, CA, United States
Duration: 6 Aug 20037 Aug 2003


  • ACTS algorithm
  • Histograms
  • Hyperspectral
  • K-means algorithm
  • Merit function
  • Principal components
  • Segmentation levels

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Issues in segmenting hyperspectral imagery from histograms'. Together they form a unique fingerprint.

Cite this