Pixel-level image fusion has been investigated in various applications and many algorithms have been proposed. However, few authors have addressed the problem of how to evaluate the performance of those algorithms. In this paper, we propose a structure similarity based objective metric for image fusion, which evaluates the similarity of the gradient fields between the source images and the fused result. Meanwhile, local information given by salience within localized windows are incorporated into the final metric. Extensive experiments demonstrate that the proposed metric can evaluate the image fusion performance effectively and is consistent with perceptually obtained results.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Structure similarity based objective metric for pixel-level image fusion


    Contributors:
    Hong, Richang (author) / Sun, Fuming (author)


    Publication date :

    2008-12-01


    Size :

    548807 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Objective pixel-level image fusion performance measure

    Xydeas, Costas S. / Petrovic, Vladimir S. | SPIE | 2000


    A feature-based metric for the quantitative evaluation of pixel-level image fusion

    Liu, Z. / Forsyth, D. S. / Laganiere, R. | British Library Online Contents | 2008


    Pixel level sensor fusion

    RATHBUN, THOMAS / WASHBURNE, T. | AIAA | 1993


    Optimizing multiresolution pixel-level image fusion [4385-13]

    Petrovic, V. S. / Xydeas, C. S. | British Library Conference Proceedings | 2001


    No-Reference Objective Wavelet Based Noise Immune Image Sharpness Metric

    Ferzli, R. / Karam, L. J. | British Library Conference Proceedings | 2005