This paper presents a novel method for detecting objects in natural images in a non-restricted domain. Our purpose here is to capture meaningful information in terms of user semantics on the visual level for efficient image retrieval. The major obstacle in developing such methods is the difficulty of accurately segmenting the image into its prominent regions. To overcome this difficulty, we developed a vector-valued inhomogeneous diffusion model that uses multiple features. In this model, we define the gradient threshold and thus the conductance parameter as a function of the texture and/or color gradient varying by evolving diffusion. The method is evaluated for 20,000 natural images taken by both professionals and amateurs and it is proved to be very robust and effective for obtaining sufficient region-based image description and thus facilitating intelligent and user-friendly image retrieval applications.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Detecting prominent objects for image retrieval


    Contributors:
    Kutics, A. (author) / Nakagawa, A. (author)


    Publication date :

    2005-01-01


    Size :

    839703 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Detecting Prominent Objects for Image Retrieval

    Kutics, A. / Nakagawa, A. | British Library Conference Proceedings | 2005


    Image Retrieval with Visually Prominent Features Using Fuzzy Set Theoretic Evaluation

    Banerjee, M. / Kundu, M. K. / Das, P. K. et al. | British Library Conference Proceedings | 2006


    Tracking prominent points in image sequences

    Hahn, M. / Institute of Geodesy and Photogrammetry / Institute of National Surveying and Engineering Geodesy et al. | British Library Conference Proceedings | 1994


    ProMinent expands in South Korea

    Online Contents | 2010


    Inspecting four prominent bridge

    Rolwood, Craig J. / Drew, Robert | IuD Bahn | 2008