This paper deals with the performance evaluation of three object invariant descriptors: Hu moments, Zernike moments and Fourier-Mellin descriptors. Experiments are conducted on a database of 100 objects extracted from the Columbia Object Image Library (COIL-100). Original images from this database only present geometric transformations. They therefore allow to quantify the scale and rotation invariances of the different features and to compare their ability to discriminate objects. In order to test the robustness of the three tested descriptors, we have completed the data set by images including different perturbations: noise, occlusion, luminance variation, backgrounds (uniform, with noise, textured) added to the object. Recognition tests are realised using a support vector machine as supervised classification method. Experimental results are summarized and analyzed permitting to compare the global performances of the different descriptors.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Comparison of invariant descriptors for object recognition


    Contributors:
    Choksuriwong, A. (author) / Laurent, H. (author) / Emile, B. (author)


    Publication date :

    2005-01-01


    Size :

    306614 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Comparison of Invariant Descriptors for Object Recognition

    Choksuriwong, A. / Laurent, H. / Emile, B. | British Library Conference Proceedings | 2005


    Comparative study of global invariant descriptors for object recognition

    Choksuriwong, A. / Emile, B. / Laurent, H. et al. | British Library Online Contents | 2008



    Using Illumination Invariant Color Histogram Descriptors for Recognition

    Healey, G. / Slater, D. / Institute of Electrical and Electronics Engineers; Computer Society | British Library Conference Proceedings | 1994


    Video-based descriptors for object recognition

    Lee, T. / Soatto, S. | British Library Online Contents | 2011