A new approach to the characterization of texture properties at multiple scales using an overcomplete wavelet transform is described. It is shown that this representation constitutes a tight frame of l/sub 2/, and that it has a fast iterative algorithm. A texture is characterized by a set of channel variances estimated at the output of the corresponding filter-bank. Classification experiments with 12 Brodatz textures indicate that the discrete wavelet frame (DWF) approach is superior to a standard (critically sampled) wavelet transform feature extraction. This result also suggests that this approach should perform better than most traditional single resolution techniques (co-occurrences, local linear transform, etc. . .). A detailed comparison of the classification performance of various orthogonal and biorthogonal wavelet transforms is provided. The DWF feature extraction technique is incorporated into a simple multiple-component texture segmentation algorithm. Some examples are presented.<>


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Texture discrimination using wavelets


    Beteiligte:
    Unser, M. (Autor:in)


    Erscheinungsdatum :

    01.01.1993


    Format / Umfang :

    183067 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Pavement macro-texture analysis using wavelets

    Zelelew, H. M. | Online Contents | 2013


    Texture analysis using Gabor wavelets [2657-10]

    Naghdy, G. A. / Wang, J. / Ogunbona, P. O. et al. | British Library Conference Proceedings | 1996



    Robust Tracking Using Foreground-Background Texture Discrimination

    Nguyen, H. T. / Smeulders, A. W. | British Library Online Contents | 2006


    Robust-to-rotation texture descriptor for image retrieval in wavelets domain

    Jiang, J. / Weng, Y. / Guo, B. et al. | British Library Online Contents | 2006