• DocumentCode
    3127920
  • Title

    Texture-based image retrieval without segmentation

  • Author

    Rubner, Yossi ; Tomasi, Carlo

  • Author_Institution
    Dept. of Comput. Sci., Stanford Univ., CA, USA
  • Volume
    2
  • fYear
    1999
  • fDate
    1999
  • Firstpage
    1018
  • Abstract
    Image segmentation is not only hard and unnecessary for texture-based image retrieval, but can even be harmful. Images of either individual or multiple textures are best described by distributions of spatial frequency descriptors, rather than single descriptor vectors over presegmented regions. A retrieval method based on the earth movers distance with an appropriate ground distance is shown to handle both complete and partial multi-textured queries. As an illustration, different images of the same type of animal are easily retrieved together. At the same time, animals with subtly different coats, like cheetahs and leopards, are properly distinguished
  • Keywords
    image retrieval; image texture; animal images; complete multi-textured queries; earth movers distance; ground distance; partial multi-textured queries; presegmented regions; spatial frequency descriptor distributions; texture-based image retrieval; Computer science; Earth; Gabor filters; Image resolution; Image retrieval; Image segmentation; Image texture; Lighting; Shape; Spatial resolution;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on
  • Conference_Location
    Kerkyra
  • Print_ISBN
    0-7695-0164-8
  • Type

    conf

  • DOI
    10.1109/ICCV.1999.790380
  • Filename
    790380