Subspace Analysis Of Arbitrarily Many Linear Filter Responses with an application to Face Tracking

Stefanos Zafeiriou, Georgios Tzimiropoulos, Maja Pantic

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

    2 Citations (Scopus)

    Abstract

    Multi-scale/orientation local image analysis methods are valuable tools for obtaining highly distinctive image-based representations. Very often, these features are generated from the responses of a bank of linear filters corresponding to different scales and orientations. Naturally, as the number of filters increases, so does the feature dimensionality. Further processing is often feasible only when dimensionality reduction is performed by subspace learning techniques, such as Principal Component analysis (PCA) or Linear Discriminant Analysis (LDA). The major problem stems from the fact that as the number of features increases, so does the computational complexity of these methods which, in turn, limits the number of scales and orientations examined. In this paper, we show how linear subspace analysis on features generated by the response of linear filter banks can be efficiently re-formulated such that complexity does not depend on the number of filters used. We describe computationally efficient and exact versions of PCA while the extension to other subspace learning algorithms is straightforward. Finally, we show how the proposed methods can boost the performance of algorithms for appearance based tracking algorithm.
    Original languageEnglish
    Title of host publicationIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR-W 2011)
    Place of PublicationUSA
    PublisherIEEE Computer Society
    Pages37-42
    Number of pages6
    ISBN (Print)978-1-4577-0529-8
    DOIs
    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

    Name
    PublisherIEEE Computer Society
    ISSN (Print)2160-7508

    Conference

    Conference24th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011
    Abbreviated titleCVPR 2011
    CountryUnited States
    CityColorado Springs
    Period20/06/1125/06/11

    Keywords

    • Channel bank filters
    • Face recognition
    • Computational complexity
    • HMI-MI: MULTIMODAL INTERACTIONS
    • Principal component analysis
    • Object tracking
    • Image representation
    • Learning (artificial intelligence)

    Fingerprint Dive into the research topics of 'Subspace Analysis Of Arbitrarily Many Linear Filter Responses with an application to Face Tracking'. Together they form a unique fingerprint.

    Cite this