• DocumentCode
    2684959
  • Title

    Robustness of a mathematical symbiotic system on segmenting SAR imagery

  • Author

    Daida, Jason M.

  • Author_Institution
    Artificial Intelligence Lab., Michigan Univ., Ann Arbor, MI, USA
  • Volume
    4
  • fYear
    1994
  • fDate
    8-12 Aug 1994
  • Firstpage
    2126
  • Abstract
    The reported work describes an experiment that evaluates the performance of a hybrid segmentation algorithm on speckled imagery. The particular hybrid algorithm considered was developed using a technique called mathematical symbiosis. The results show that the algorithm is able to correctly extract whole region shapes from the test images, even if the region shapes were almost adjoining each other. The results also show that the algorithm yields misclassification error rates that are below four percent for most of the test images
  • Keywords
    geophysical signal processing; geophysical techniques; image classification; image segmentation; radar applications; radar imaging; remote sensing by radar; spaceborne radar; speckle; synthetic aperture radar; SAR imagery; SAR imaging; geophysical measurement technique; hybrid algorithm; hybrid segmentation algorithm; image classification; image region analysis; image segmentation; mathematical symbiosis; mathematical symbiotic system; misclassification error rates; radar remote sensing; region shape; robust method; robustness; spaceborne radar; speckled imagery; synthetic aperture radar; terrain mapping land surface; Artificial intelligence; Benchmark testing; Clustering algorithms; Computer architecture; Data mining; Image segmentation; Laboratories; Robustness; Shape; Symbiosis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Geoscience and Remote Sensing Symposium, 1994. IGARSS '94. Surface and Atmospheric Remote Sensing: Technologies, Data Analysis and Interpretation., International
  • Conference_Location
    Pasadena, CA
  • Print_ISBN
    0-7803-1497-2
  • Type

    conf

  • DOI
    10.1109/IGARSS.1994.399670
  • Filename
    399670