Current automated intensity-based registration procedures make use of similarity functions computed with joint histograms, such as the well-known mutual information or the recent correlation ratio. We notice that the computation of such histograms represents up to 90% of time of the whole process. We propose in this work a method to accelerate the computation of these histograms in the case of affine transformations, with a slight loss of accuracy. An analytical model of the new computation time allows us to find optimal parameters for a chosen precision and to predict the performance of the algorithm. Experimental results show that the speedup is greater than three with the partial volume interpolation method or near ten with the nearest neighbor distribution, without significant loss of precision in the final result.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Fast 3D image transformations for registration procedures


    Beteiligte:
    Sarrut, D. (Autor:in) / Miguet, S. (Autor:in)


    Erscheinungsdatum :

    01.01.1999


    Format / Umfang :

    126748 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Fast 3D Image Transformations for Registration Procedures

    Sarrut, D. / Miguet, S. / IEEE | British Library Conference Proceedings | 1999


    Algorithms for Fast Image Registration

    Rezaie, B. / Srinath, M.D. | IEEE | 1984


    Fast remote sensing image registration algorithm

    Yue, T. / Yongmei, Z. / Bo, L. | British Library Online Contents | 2008


    Shear-resize factorizations for fast image registration

    Chen Ying, / Pengwei Hao, / Chao Zhang, | IEEE | 2005


    Shear-Resize Factorizations for Fast Image Registration

    Chen, Y. / Hao, P. / Zhang, C. | British Library Conference Proceedings | 2005