Texture-based image retrieval without segmentation
Publication
, Journal Article
Rubner, Y; Tomasi, C
Published in: Proceedings of the IEEE International Conference on Computer Vision
January 1, 1999
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.
Duke Scholars
Published In
Proceedings of the IEEE International Conference on Computer Vision
DOI
ISSN
1550-5499
Publication Date
January 1, 1999
Volume
2
Start / End Page
1018 / 1024
Citation
APA
Chicago
ICMJE
MLA
NLM
Rubner, Y., & Tomasi, C. (1999). Texture-based image retrieval without segmentation. Proceedings of the IEEE International Conference on Computer Vision, 2, 1018–1024. https://doi.org/10.1109/iccv.1999.790380
Rubner, Y., and C. Tomasi. “Texture-based image retrieval without segmentation.” Proceedings of the IEEE International Conference on Computer Vision 2 (January 1, 1999): 1018–24. https://doi.org/10.1109/iccv.1999.790380.
Rubner Y, Tomasi C. Texture-based image retrieval without segmentation. Proceedings of the IEEE International Conference on Computer Vision. 1999 Jan 1;2:1018–24.
Rubner, Y., and C. Tomasi. “Texture-based image retrieval without segmentation.” Proceedings of the IEEE International Conference on Computer Vision, vol. 2, Jan. 1999, pp. 1018–24. Scopus, doi:10.1109/iccv.1999.790380.
Rubner Y, Tomasi C. Texture-based image retrieval without segmentation. Proceedings of the IEEE International Conference on Computer Vision. 1999 Jan 1;2:1018–1024.
Published In
Proceedings of the IEEE International Conference on Computer Vision
DOI
ISSN
1550-5499
Publication Date
January 1, 1999
Volume
2
Start / End Page
1018 / 1024