BIROn - Birkbeck Institutional Research Online

    Enhanced biologically inspired model

    Huang, Y. and Huang, K. and Wang, L. and Tao, D. and Tan, T. and Li, Xuelong (2008) Enhanced biologically inspired model. In: UNSPECIFIED (ed.) Conference on Computer Vision and Pattern Recognition. New York, USA: Institute of Electrical and Electronics Engineers, pp. 1-8. ISBN 9781424422425.

    Full text not available from this repository.

    Abstract

    It has been demonstrated by Serre et al. that the biologically inspired model (BIM) is effective for object recognition. It outperforms many state-of-the-art methods in challenging databases. However, BIM has the following three problems: a very heavy computational cost due to dense input, a disputable pooling operation in modeling relations of the visual cortex, and blind feature selection in a feed-forward framework. To solve these problems, we develop an enhanced BIM (EBIM), which removes uninformative input by imposing sparsity constraints, utilizes a novel local weighted pooling operation with stronger physiological motivations, and applies a feedback procedure that selects effective features for combination. Empirical studies on the CalTech5 database and CalTech101 database show that EBIM is more effective and efficient than BIM. We also apply EBIM to the MIT-CBCL street scene database to show it achieves comparable performance in comparison with the current best performance. Moreover, the new system can process images with resolution 128 times 128 at a rate of 50 frames per second and enhances the speed 20 times at least in comparison with BIM in common applications.

    Metadata

    Item Type: Book Section
    School: School of Business, Economics & Informatics > Computer Science and Information Systems
    Depositing User: Sarah Hall
    Date Deposited: 11 Jul 2013 16:36
    Last Modified: 11 Oct 2016 15:27
    URI: https://eprints.bbk.ac.uk/id/eprint/7663

    Statistics

    Downloads
    Activity Overview
    0Downloads
    125Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item