The Gaussian kernel has played a central role in multi-scale methods for feature extraction and matching. In this paper, a method for shaping the filter using the local image structure is presented. We propose an optimization formulation that densely estimates the filter's affine parameters by minimizing an objective constructed from differential feature responses and seek iterative, approximate solutions. A consequence of shaping the filters is affine invariance of the differential feature vector and it is shown that the shaped responses improve recognition performance.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Shaping receptive fields for affine invariance


    Contributors:
    Ravela, S. (author)


    Publication date :

    2004-01-01


    Size :

    323674 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Shaping Receptive Fields for Affine Invariance

    Ravela, S. / IEEE Computer Society | British Library Conference Proceedings | 2004


    Coplanar circles, quasi-affine invariance and calibration

    Wu, Y. / Li, X. / Wu, F. et al. | British Library Online Contents | 2006


    Turning a blind eye to cortical receptive fields

    Chapman, B. / Stone, L. S. | NTRS | 1996


    Linear Neural Circuitry Model for Visual Receptive Fields

    Mahmoodi, S. | British Library Online Contents | 2016


    Time-Causal and Time-Recursive Spatio-Temporal Receptive Fields

    Lindeberg, T. | British Library Online Contents | 2016