Maximization of mutual information is a powerful method for registering images (and other data) captured with different sensors or under varying conditions, since the technique is robust to variations in the image formation process. On the other hand, the high level of robustness allows false positives when matching over a large search space and also makes it difficult to formulate an efficient search strategy for this case. We describe techniques to overcome these problems by aligning image entropies, which are robust to illumination variation and can be applied to multi-sensor registration. This results in a lower rate of false positives and a more efficient method to search an image for the matching position. The techniques are applied to real imagery and compared to methods based on mutual information and gradients to demonstrate their effectiveness.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Image registration by aligning entropies


    Contributors:
    Olson, C.F. (author)


    Publication date :

    2001-01-01


    Size :

    1356730 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Image Registration by Aligning Entropies

    Olson, C. F. / IEEE | British Library Conference Proceedings | 2001



    Image registration

    Petrou, Maria / Lazaridis, George | SPIE | 2003


    Quantum and classical inequalities for tomographic entropies

    Man’ko, M. A. | British Library Online Contents | 2009


    Deformable image registration

    Jian-Kun Shen, / Matuszewski, B.J. / Lik-Kwan Shark, | IEEE | 2005