Abstract Scale and affine-invariant local features have shown excellent performance in image matching, object and texture recognition. This paper optimizes keypoint detection to achieve stable local descriptors, and therefore, an improved image representation. The technique performs scale selection based on a region descriptor, here SIFT, and chooses regions for which this descriptor is maximally stable. Maximal stability is obtained, when the difference between descriptors extracted for consecutive scales reaches a minimum. This scale selection technique is applied to multi-scale Harris and Laplacian points. Affine invariance is achieved by an integrated affine adaptation process based on the second moment matrix. An experimental evaluation compares our detectors to Harris-Laplace and the Laplacian in the context of image matching as well as of category and texture classification. The comparison shows the improved performance of our detector.


    Access

    Download


    Export, share and cite



    Title :

    Maximally Stable Local Description for Scale Selection


    Contributors:


    Publication date :

    2006-01-01


    Size :

    13 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Maximally Stable Local Description for Scale Selection

    Dorko, G. / Schmid, C. | British Library Conference Proceedings | 2006


    Maximally Stable Control and reconstruction

    Vaněček, A. | TIBKAT | 1984


    Robust wide-baseline stereo from maximally stable extremal regions

    Matas, J. / Chum, O. / Urban, M. et al. | British Library Online Contents | 2004


    MULTI-SENSOR SELF-LOCALIZATION BASED ON MAXIMALLY STABLE EXTREMAL REGIONS

    Deusch, H. / Wiest, J. / Reuter, S. et al. | British Library Conference Proceedings | 2014


    Pedestrian Detection Based on Maximally Stable Extremal Regions, pp. 910-914

    Frolov, V. / Puente Leon, F. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2010