Image inpainting provides a means to restore damaged region of an image, such that the image looks complete and natural after the inpainting process. This paper presents a new inpainting algorithm, which implements the filling of damaged region based on morphological erosion and structure feature replication. The method, which is based on a structure/texture feature matching algorithm, can retain isophote continuity by propagating both texture and structure characteristics information of the known patch into the damaged region, and output a complete, natural-looking and non-blurred image. By implementing region-filling through morphological erosion, several pixels instead of one can be restored at every inpainting step, making the method faster than many traditional texture synthesis inpainting algorithms. We demonstrate through several examples the effectiveness of the algorithm in removing large occluding objects as well as thin scratches.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Structure-Synthesis Image Inpainting Algorithm Based on Morphological Erosion Operation


    Contributors:


    Publication date :

    2008-05-01


    Size :

    631099 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Fast Orientation-Driven Multi-Structure Morphological Inpainting

    Deva, Jemi Florinabel / Selwyn, Ebenezer Juliet / Velayuthum, Sadasivam | British Library Online Contents | 2012


    Fast Orientation-Driven Multi-Structure Morphological Inpainting

    Deva, J.F. / Selwyn, E.J. / Velayuthum, S. | British Library Online Contents | 2012


    Em Algorithm for Sparse Representation-Based Image Inpainting

    Fadill, M. J. / Starck, J.-L. | British Library Conference Proceedings | 2005


    EM algorithm for sparse representation-based image inpainting

    Fadili, M.J. / Starck, J.-L. | IEEE | 2005


    CNN-Based Stereoscopic Image Inpainting

    Chen, Shen / Ma, Wei / Qin, Yue | British Library Conference Proceedings | 2019