Sparse Representations of Image Gradient Orientations for Visual Recognition and Tracking

Georgios Tzimiropoulos, Stefanos Zafeiriou, Maja Pantic

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    24 Citations (Scopus)


    Recent results have shown that sparse linear representations of a query object with respect to an overcomplete basis formed by the entire gallery of objects of interest can result in powerful image-based object recognition schemes. In this paper, we propose a framework for visual recognition and tracking based on sparse representations of image gradient orientations. We show that minimal ℓ1 solutions to problems formulated with gradient orientations can be used for fast and robust object recognition even for probe objects corrupted by outliers. These solutions are obtained without the need for solving the extended problem considered in. We further show that low-dimensional embeddings generated from gradient orientations perform equally well even when probe objects are corrupted by outliers, which, in turn, results in huge computational savings. We demonstrate experimentally that, compared to the baseline method in, our formulation results in better recognition rates without the need for block processing and even with smaller number of training samples. Finally, based on our results, we also propose a robust and efficient ℓ1-based “tracking by detection‿ algorithm. We show experimentally that our tracker outperforms a recently proposed ℓ1-based tracking algorithm in terms of robustness, accuracy and speed.
    Original languageEnglish
    Title of host publicationIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR-W 2011)
    Place of PublicationPiscataway, NJ
    PublisherIEEE Computer Society
    Number of pages8
    ISBN (Print)978-1-4577-0529-8
    Publication statusPublished - Jun 2011
    Event24th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011 - Colorado Springs, United States
    Duration: 20 Jun 201125 Jun 2011
    Conference number: 24

    Publication series

    PublisherIEEE Computer Society
    ISSN (Print)2160-7508


    Conference24th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011
    Abbreviated titleCVPR 2011
    CountryUnited States
    CityColorado Springs


    • METIS-285031
    • IR-79435
    • Dictionaries
    • Visualization
    • Probes
    • Object recognition
    • Testing
    • Training
    • EWI-21331
    • EC Grant Agreement nr.: ERC/203143
    • Robustness

    Fingerprint Dive into the research topics of 'Sparse Representations of Image Gradient Orientations for Visual Recognition and Tracking'. Together they form a unique fingerprint.

    Cite this