BIROn - Birkbeck Institutional Research Online

    Image classification using multiscale information fusion based on saliency driven nonlinear diffusion filtering

    Hu, W. and Hu, R. and Xie, N. and Ling, H. and Maybank, Stephen J. (2014) Image classification using multiscale information fusion based on saliency driven nonlinear diffusion filtering. IEEE Transactions on Image Processing 23 (4), pp. 1513-1526. ISSN 1057-7149.

    [img]
    Preview
    Text
    13322.pdf - Author's Accepted Manuscript

    Download (1MB) | Preview

    Abstract

    In this paper, we propose saliency driven image multiscale nonlinear diffusion filtering. The resulting scale space in general preserves or even enhances semantically important structures such as edges, lines, or flow-like structures in the foreground, and inhibits and smoothes clutter in the background. The image is classified using multiscale information fusion based on the original image, the image at the final scale at which the diffusion process converges, and the image at a midscale. Our algorithm emphasizes the foreground features, which are important for image classification. The background image regions, whether considered as contexts of the foreground or noise to the foreground, can be globally handled by fusing information from different scales. Experimental tests of the effectiveness of the multiscale space for the image classification are conducted on the following publicly available datasets: 1) the PASCAL 2005 dataset; 2) the Oxford 102 flowers dataset; and 3) the Oxford 17 flowers dataset, with high classification rates.

    Metadata

    Item Type: Article
    Additional Information: (c) 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, 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 components of this work in other works.
    School: Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences
    Depositing User: Administrator
    Date Deposited: 03 Nov 2015 15:35
    Last Modified: 09 Aug 2023 12:37
    URI: https://eprints.bbk.ac.uk/id/eprint/13322

    Statistics

    Activity Overview
    6 month trend
    499Downloads
    6 month trend
    209Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item