• DocumentCode
    261797
  • Title

    Evaluation of Bag-of-Colors descriptor for land use classification

  • Author

    Jovanovic, Vedran ; Risojevic, Vladimir

  • Author_Institution
    Fac. of Electr. Eng., Univ. of Banja Luka, Banja Luka, Bosnia-Herzegovina
  • fYear
    2014
  • fDate
    25-27 Nov. 2014
  • Firstpage
    889
  • Lastpage
    892
  • Abstract
    The objective of this paper is to evaluate Bag-of-Colors (BoC) descriptor for land use classification. BoC can be used either as a global or local descriptor. In this paper we present and evaluate both approaches. We analyze the influence of different parameters on classification accuracy and introduce a modification of descriptor extraction process, which significantly influences the classification results and performance.
  • Keywords
    feature extraction; image classification; image colour analysis; descriptor extraction process modification; global BoC descriptor evaluation; image classification; land use classification; local bag-of-colors descriptor; Accuracy; Histograms; Image color analysis; Quantization (signal); Support vector machines; Testing; Training; BoC descriptor; Land Use Classification; color descriptors;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Telecommunications Forum Telfor (TELFOR), 2014 22nd
  • Conference_Location
    Belgrade
  • Print_ISBN
    978-1-4799-6190-0
  • Type

    conf

  • DOI
    10.1109/TELFOR.2014.7034547
  • Filename
    7034547