Improving SIFT-based descriptors stability to rotations

Fabio Bellavia, Domenico Tegolo, Emanuele Trucco

    Research output: Chapter in Book/Report/Conference proceedingOther chapter contribution

    19 Citations (Scopus)

    Abstract

    Image descriptors are widely adopted structures to match image features. SIFT-based descriptors are collections of gradient orientation histograms computed on different feature regions, commonly divided by using a regular Cartesian grid or a log-polar grid. In order to achieve rotation invariance, feature patches have to be generally rotated in the direction of the dominant gradient orientation. In this paper we present a modification of the GLOH descriptor, a SIFT-based descriptor based on a log-polar grid, which avoids to rotate the feature patch before computing the descriptor since predefined discrete orientations can be easily derived by shifting the descriptor vector. The proposed descriptors, called sGLOH and sGLOH+, have been compared with the SIFT descriptor on the Oxford image dataset, with good results which point out its robustness and stability.
    Original languageEnglish
    Title of host publication2010 20th International Conference on Pattern Recognition, ICPR 2010
    Subtitle of host publicationproceedings
    Place of PublicationPiscataway
    PublisherIEEE Computer Society
    Pages3460-3463
    Number of pages4
    ISBN (Print)9780769541099
    DOIs
    Publication statusPublished - 2010
    Event20th International Conference on Pattern Recognition - Istanbul, Turkey
    Duration: 23 Aug 201026 Aug 2010

    Publication series

    NameInternational Conference on Pattern Recognition
    PublisherIEEE Computer Society
    ISSN (Print)1051-4651

    Conference

    Conference20th International Conference on Pattern Recognition
    Abbreviated titleICPR 2010
    CountryTurkey
    CityIstanbul
    Period23/08/1026/08/10

    Keywords

    • Cartesian grid
    • Descriptors
    • Gradient orientations
    • Image datasets
    • Image descriptors
    • Image features
    • Log-polar
    • Rotation invariance
    • Pattern recognition

    Fingerprint Dive into the research topics of 'Improving SIFT-based descriptors stability to rotations'. Together they form a unique fingerprint.

    Cite this