Research

Discriminative learning of local image descriptors


Reference:

Brown, M. A., Hua, G. and Winder, S., 2011. Discriminative learning of local image descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33 (1), pp. 43-57.

Related documents:

[img]
Preview
PDF (Brown_IEEE-TPAMI_2011_33_1_43.pdf) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (10MB) | Preview

    Official URL:

    http://dx.doi.org/10.1109/TPAMI.2010.54

    Abstract

    In this paper, we explore methods for learning local image descriptors from training data. We describe a set of building blocks for constructing descriptors which can be combined together and jointly optimized so as to minimize the error of a nearest-neighbor classifier. We consider both linear and nonlinear transforms with dimensionality reduction, and make use of discriminant learning techniques such as Linear Discriminant Analysis (LDA) and Powell minimization to solve for the parameters. Using these techniques, we obtain descriptors that exceed state-of-the-art performance with low dimensionality. In addition to new experiments and recommendations for descriptor learning, we are also making available a new and realistic ground truth data set based on multiview stereo data.

    Details

    Item Type Articles
    CreatorsBrown, M. A., Hua, G. and Winder, S.
    DOI10.1109/TPAMI.2010.54
    DepartmentsFaculty of Science > Computer Science
    Publisher StatementBrown_IEEE-TPAMI_2011_33_1_43.pdf: © 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
    RefereedYes
    StatusPublished
    ID Code26111

    Export

    Actions (login required)

    View Item

    Document Downloads

    More statistics for this item...