BIROn - Birkbeck Institutional Research Online

    Beyond spatial pyramids: a new feature extraction framework with dense spatial sampling for image classification

    Yan, S. and Xu, X. and Xu, D. and Lin, S. and Li, Xuelong (2012) Beyond spatial pyramids: a new feature extraction framework with dense spatial sampling for image classification. In: Fitzgibbon, A. and Lazebnik, S. and Perona, P. and Sato, Y. and Schmid, C. (eds.) Computer Vision. Lecture Notes in Computer Science 7575. Berlin, Germany: Springer Verlag, pp. 473-487. ISBN 9783642337659.

    Full text not available from this repository.


    We introduce a new framework for image classification that extends beyond the window sampling of fixed spatial pyramids to include a comprehensive set of windows densely sampled over location, size and aspect ratio. To effectively deal with this large set of windows, we derive a concise high-level image feature using a two-level extraction method. At the first level, window-based features are computed from local descriptors (e.g., SIFT, spatial HOG, LBP) in a process similar to standard feature extractors. Then at the second level, the new image feature is determined from the window-based features in a manner analogous to the first level. This higher level of abstraction offers both efficient handling of dense samples and reduced sensitivity to misalignment. More importantly, our simple yet effective framework can readily accommodate a large number of existing pooling/coding methods, allowing them to extract features beyond the spatial pyramid representation. To effectively fuse the second level feature with a standard first level image feature for classification, we additionally propose a new learning algorithm, called Generalized Adaptive ℓ p -norm Multiple Kernel Learning (GA-MKL), to learn an adapted robust classifier based on multiple base kernels constructed from image features and multiple sets of pre-learned classifiers of all the classes. Extensive evaluation on the object recognition (Caltech256) and scene recognition (15Scenes) benchmark datasets demonstrates that the proposed method outperforms state-of-the-art image classification algorithms under a broad range of settings.


    Item Type: Book Section
    School: Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences
    Depositing User: Sarah Hall
    Date Deposited: 06 Jun 2013 15:42
    Last Modified: 09 Aug 2023 12:33


    Activity Overview
    6 month trend
    6 month trend

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item