Image has various inherent features which reflect its content such as color, texture, shape, spatial relationship features etc How to organize and utilize these features effectively and improve the retrieval performance is a valuable research topic in content-based image retrieval. One of the key issues in image retrieval based on combined features is how to assign weight to different feature. An image retrieval method combined color and texture features is proposed in this paper. According to image texture characteristic, a kind of image feature statistic is defined. By using feature weight assignment operators designed here, the method can assign weight to the color and texture features according to image content adaptively and realize image retrieval based on combined image features. The experiment results show that the method is more efficiently than those traditional CBIR methods based on single visual feature or simple linear combined low-level visual features of fixed weight


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A New Image Retrieval Method Based on Combined Features and Feature Statistic


    Beteiligte:
    Liu, Pengyu (Autor:in) / Jia, Kebin (Autor:in) / Wang, Zhuozheng (Autor:in)


    Erscheinungsdatum :

    2008-05-01


    Format / Umfang :

    742630 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Dense statistic versus sparse feature-based approach for 3D object recognition

    Decker, P. / Thierfelder, S. / Paulus, D. et al. | British Library Online Contents | 2011


    Image Retrieval: Feature Primitives, Feature Representation, and Relevance Feedback

    Zhou, X. / Huang, T. / IEEE | British Library Conference Proceedings | 2000



    Statistical Shape Features for Content-Based Image Retrieval

    Brandt, S. / Laaksonen, J. / Oja, E. | British Library Online Contents | 2002