We present a framework for texture recognition based on local affine-invariant descriptors and their spatial layout. At modelling time, a generative model of local descriptors is learned from sample images using the EM algorithm. The EM framework allows the incorporation of unsegmented multitexture images into the training set. The second modelling step consists of gathering co-occurrence statistics of neighboring descriptors. At recognition time, initial probabilities computed from the generative model are refined using a relaxation step that incorporates co-occurrence statistics. Performance is evaluated on images of an indoor scene and pictures of wild animals.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Affine-invariant local descriptors and neighborhood statistics for texture recognition


    Contributors:
    Lazebnik, (author) / Schmid, (author) / Ponce, (author)


    Publication date :

    2003-01-01


    Size :

    1101205 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Affine-Invariant Local Descriptors and Neighborhood Statistics for Texture Recognition

    Lazebnik, S. / Schmid, C. / Ponce, J. et al. | British Library Conference Proceedings | 2003


    Illumination invariant optical flow using neighborhood descriptors

    Ali, Sharib / Daul, Christian / Galbrun, Ernest et al. | British Library Online Contents | 2016


    Illumination invariant optical flow using neighborhood descriptors

    Ali, Sharib / Daul, Christian / Galbrun, Ernest et al. | British Library Online Contents | 2016


    Affine invariant descriptors using principal components analysis

    Oirrak, A. | British Library Online Contents | 2008


    Ear biometric recognition using local texture descriptors

    Benzaoui, A. / Hadid, A. / Boukrouche, A. | British Library Online Contents | 2014