Human-centered object-based image retrieval

Egon van den Broek, Sameer Singh (Editor), Eva M. van Rikxoort, Maneesha Singh (Editor), Theo E. Schouten, Chid Apte (Editor), Petra Perner (Editor)

    Research output: Contribution to conferencePaper

    10 Citations (Scopus)
    8 Downloads (Pure)


    A new object-based image retrieval (OBIR) scheme is introduced. The images are analyzed using the recently developed, human-based 11 colors quantization scheme and the color correlogram. Their output served as input for the image segmentation algorithm: agglomerative merging, which is extended to color images. From the resulting coarse segments, boundaries are extracted by pixelwise classification, which are smoothed by erosion and dilation operators. The resulting features of the extracted shapes, completed the data for a <color, texture, shape>-vector. Combined with the intersection distance measure, this vector is used for OBIR, as are its components. Although shape matching by itself provides good results, the complete vector outperforms its components, with up to 80% precision. Hence, a unique, excellently performing, fast, on human perception based, OBIR scheme is achieved.
    Original languageUndefined
    Number of pages10
    Publication statusPublished - 22 Aug 2005


    • IR-78702
    • Color
    • EWI-20849
    • Content-Based Image Retrieval (CBIR)
    • object-based image retrieval (OBIR)
    • shape matching
    • Texture
    • pixelwise classification

    Cite this

    van den Broek, E., Singh, S. (Ed.), van Rikxoort, E. M., Singh, M. (Ed.), Schouten, T. E., Apte, C. (Ed.), & Perner, P. (Ed.) (2005). Human-centered object-based image retrieval. 492-501.