Multi-pixel anomaly detection in noisy multiSpectral images

Research output: Contribution to journalConference articlepeer-review


Basing ourselves on a novel segmentation algorithm for multi-spectral images, we have considered how to detect multi-pixel anomalous objects in image cubes with a spectral component. In particular, we have developed several filters to compensate for noise which may be present in the initial cube. We show that for speckle noise, a modification of our morphology technique allows us to detect targets without an enhanced false alarm result.

Original languageEnglish
Article number50
Pages (from-to)390-399
Number of pages10
JournalProceedings of SPIE - The International Society for Optical Engineering
StatePublished - 1 Dec 2004
EventImaging Spectrometry X - Denver, CO, United States
Duration: 2 Aug 20044 Aug 2004


  • Anomaly detection
  • Morphological operation
  • Speckle noise
  • Spectral data

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 'Multi-pixel anomaly detection in noisy multiSpectral images'. Together they form a unique fingerprint.

Cite this