This paper addresses the well-known problem of natural image matting. It proposes a whole new framework that could effectively deals with the confused boundaries such as hair, furs and other complicated situations. We take the natural image matting problem as a pattern recognition problem and use the recently developed non-negative matrix factorization technique to solve it. Experimental results show that our approach could properly handle the confused boundaries. Compared with other algorithms visually, the results of our algorithm are comparable to the algorithms that are the best of nowadays.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Natural image matting with non-negative matrix factorization


    Contributors:
    Wang Kun, (author) / Zhang Nanning, (author) / Liu Weixiang, (author)


    Publication date :

    2005-01-01


    Size :

    294596 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Natural Image Matting with Non-Negative Matrix Factorization

    Kun, W. / Nanning, Z. / Weixiang, L. | British Library Conference Proceedings | 2005


    Natural image matting through overlapping neighborhood propagation [8350-118]

    Peng, H. / Duan, J. / Yuan, J. et al. | British Library Conference Proceedings | 2012


    Image and Video Matting with Membership Propagation

    Du, Weiwei / Urahama, Kiichi | Springer Verlag | 2007



    Image Matting for Automatic Target Recognition

    Hyun-Woong Cho / Young-Rae Cho / Woo-Jin Song et al. | IEEE | 2017