• DocumentCode
    1808274
  • Title

    Region-based multi-spectral image segmentation using evolutionary strategies

  • Author

    Sabokrou, Mohammad ; Fayyazi, Hossein ; Hosseini, Mojtaba ; Fallahi, Naser

  • Author_Institution
    Dept. of ICT, Malek-Ashtar Univ. of Technol., Tehran, Iran
  • Volume
    4
  • fYear
    2011
  • fDate
    24-26 Dec. 2011
  • Firstpage
    2854
  • Lastpage
    2858
  • Abstract
    One of the most important stages of image processing is image segmentation to extract different features. In this paper, we present a region-based algorithm for multi spectral image segmentation using evolutionary strategies (ESs). We use ES to find the center of regions of the image and then classify it using Euclidean or angular distances. We also use different indices to evaluate the fitness of the resulted centers of ES (chromosomes) and compare their results to choose the best.
  • Keywords
    evolutionary computation; feature extraction; image segmentation; ES; Euclidean distances; angular distances; evolutionary strategies; feature extraction; image processing; region-based multi-spectral image segmentation; Algorithm design and analysis; Electronic mail; Image segmentation; Partitioning algorithms; Evolutionary Strategies; image segmentation; multi-spectral images; region-based segmentation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Science and Network Technology (ICCSNT), 2011 International Conference on
  • Conference_Location
    Harbin
  • Print_ISBN
    978-1-4577-1586-0
  • Type

    conf

  • DOI
    10.1109/ICCSNT.2011.6182558
  • Filename
    6182558
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1808274