Although linear representations of images are widely used in appearance-based recognition of objects, the frequently used ideas, such as PCA, ICA, and FDA, are often found to be suboptimal. A stochastic search algorithm has been proposed recently [4] for finding representations that are optimal for specific tasks and datasets. However, this search algorithm is computationally efficient only when the image size is relatively small. Here we propose a hierarchical learning algorithm to speed up the search. The proposed approach decomposes the original optimization problem into several stages according to a hierarchical organization. In particular, the following idea is applied recursively: (i) reduce the image dimension using a shrinkage matrix, (ii) optimize the recognition performance in the reduced space, and (iii)expand the optimal subspace to the bigger space in a pre-specified way. We show that the optimal performance is maintained in the last step. By applying this decomposition procedure recursively, a hierarchy of layers is formed. This speeds up the original algorithm significantly since the search is performed mainly in reduced spaces. The effectiveness of hierarchical learning is illustrated on a popular database, where the computation time is reduced by a large factor compared to the original algorithm.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Statistical Search for Hierarchical Linear Optimal Representations of Images


    Beteiligte:
    Zhang, Qiang (Autor:in) / Liu, Xiuwen (Autor:in) / Srivastava, Anuj (Autor:in)


    Erscheinungsdatum :

    01.06.2003


    Format / Umfang :

    261797 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Optimal linear representations of images for object recognition

    Xiuwen Liu, / Srivastava, A. / Gallivan, K. | IEEE | 2003


    Optimal Linear Representations of Images for Object Recognition

    Liu, X. / Srivastava, A. / Gallivan, K. et al. | British Library Conference Proceedings | 2003


    Optimal threshold selection in hierarchical coders for images and video

    Fatemi, S.H. / Mersereau, R.M. / Truong, K.K. | IEEE | 1994


    Optimal Threshold Selection in Hierarchical Coders for Images and Video

    Fatemi, S. H. / Mersereau, R. M. / Truong, K. K. et al. | British Library Conference Proceedings | 1994


    Refining action segmentation with hierarchical video representations

    Ahn, Hyemin / Lee, Dongheui | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2021

    Freier Zugriff