The aim of salient point detection is to find distinctive events in images. Salient features are generally determined from the local differential structure of images. They focus on the shape saliency of the local neighborhood. The majority of these detectors is luminance based which has the disadvantage that the distinctiveness of the local color information is completely ignored. To fully exploit the possibilities of color image salient point detection, color distinctiveness should be taken into account next to shape distinctiveness. In this paper color distinctiveness is explicitly incorporated into the design of saliency detection. The algorithm, called color saliency boosting, is based on an analysis of the statistics of color image derivatives. Isosalient color derivatives can be closely approximated by ellipsoidal surfaces in color derivative space. Based on this remarkable statistical finding, isosalient derivatives are transformed by color boosting to have equal impact on the saliency. Color saliency boosting is designed as a generic method easily adaptable to existing feature detectors. Results show that substantial improvements in information content are acquired by targeting color salient features. Further, the generality of the method is illustrated by applying color boosting to multiple existing saliency methods.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Boosting saliency in color image features


    Contributors:


    Publication date :

    2005-01-01


    Size :

    589635 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Saliency field map construction for region-of-interest-based color image querying

    Celenk, M. / Zhou, Q. / Vetnes, V. et al. | British Library Online Contents | 2005


    Saliency, Scale and Image Description

    Kadir, T. / Brady, M. | British Library Online Contents | 2001



    Saliency and KAZE features assisted object segmentation

    Mukherjee, Prerana / Lall, Brejesh | British Library Online Contents | 2017


    Probability-based saliency detection approach for multi-features integration

    Pan, Jing / He, Yuqing / Zhang, Qishen et al. | SPIE | 2015