Chromaticity Space for Illuminant Invariant Recognition

Sivalogeswaran Ratnasingam, TM McGinnity

    Research output: Contribution to journalArticle

    12 Citations (Scopus)

    Abstract

    In this paper an algorithm is proposed to extract two illuminant invariant chromaticity features from three image sensor responses. This algorithm extracts these chromaticity features at pixel level therefore it can work well in scenes illuminated with non-uniform illuminant. An approach is proposed to use the algorithm with cameras of unknown sensitivity functions. The algorithm was tested for separability of perceptually similar colours under International Commission on Illumination (CIE) standard illuminants and obtained a good performance. The algorithm was also tested for colour based object recognition by illuminating typical indoor illuminants. The proposed algorithm gives a better performance compared to other existing algorithms investigated. Finally, the algorithm was tested for skin detection invariant to illuminant, ethnic background and imaging device. In this investigation daylight scenes under different weather conditions and scenes illuminated by typical indoor illuminants were used. The proposed algorithm gives a better skin detection performance compared to widely used standard colour spaces. Based on the results presented, the proposed illuminant invariant chromaticity space can be used for machine vision applications including illuminant invariant colour based object recognition and skin detection.
    LanguageEnglish
    Pages3612 -3623
    JournalIEEE Transactions on Image Processing
    Volume21
    Issue number8
    DOIs
    Publication statusPublished - 2012

    Fingerprint

    Color
    Skin
    Object recognition
    Image sensors
    Computer vision
    Lighting
    Pixels
    Cameras
    Imaging techniques

    Cite this

    Ratnasingam, Sivalogeswaran ; McGinnity, TM. / Chromaticity Space for Illuminant Invariant Recognition. 2012 ; Vol. 21, No. 8. pp. 3612 -3623.
    @article{37cdf97ca8d94abcb075233e474bfb32,
    title = "Chromaticity Space for Illuminant Invariant Recognition",
    abstract = "In this paper an algorithm is proposed to extract two illuminant invariant chromaticity features from three image sensor responses. This algorithm extracts these chromaticity features at pixel level therefore it can work well in scenes illuminated with non-uniform illuminant. An approach is proposed to use the algorithm with cameras of unknown sensitivity functions. The algorithm was tested for separability of perceptually similar colours under International Commission on Illumination (CIE) standard illuminants and obtained a good performance. The algorithm was also tested for colour based object recognition by illuminating typical indoor illuminants. The proposed algorithm gives a better performance compared to other existing algorithms investigated. Finally, the algorithm was tested for skin detection invariant to illuminant, ethnic background and imaging device. In this investigation daylight scenes under different weather conditions and scenes illuminated by typical indoor illuminants were used. The proposed algorithm gives a better skin detection performance compared to widely used standard colour spaces. Based on the results presented, the proposed illuminant invariant chromaticity space can be used for machine vision applications including illuminant invariant colour based object recognition and skin detection.",
    author = "Sivalogeswaran Ratnasingam and TM McGinnity",
    year = "2012",
    doi = "10.1109/TIP.2012.2193135",
    language = "English",
    volume = "21",
    pages = "3612 --3623",
    number = "8",

    }

    Chromaticity Space for Illuminant Invariant Recognition. / Ratnasingam, Sivalogeswaran; McGinnity, TM.

    Vol. 21, No. 8, 2012, p. 3612 -3623.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Chromaticity Space for Illuminant Invariant Recognition

    AU - Ratnasingam, Sivalogeswaran

    AU - McGinnity, TM

    PY - 2012

    Y1 - 2012

    N2 - In this paper an algorithm is proposed to extract two illuminant invariant chromaticity features from three image sensor responses. This algorithm extracts these chromaticity features at pixel level therefore it can work well in scenes illuminated with non-uniform illuminant. An approach is proposed to use the algorithm with cameras of unknown sensitivity functions. The algorithm was tested for separability of perceptually similar colours under International Commission on Illumination (CIE) standard illuminants and obtained a good performance. The algorithm was also tested for colour based object recognition by illuminating typical indoor illuminants. The proposed algorithm gives a better performance compared to other existing algorithms investigated. Finally, the algorithm was tested for skin detection invariant to illuminant, ethnic background and imaging device. In this investigation daylight scenes under different weather conditions and scenes illuminated by typical indoor illuminants were used. The proposed algorithm gives a better skin detection performance compared to widely used standard colour spaces. Based on the results presented, the proposed illuminant invariant chromaticity space can be used for machine vision applications including illuminant invariant colour based object recognition and skin detection.

    AB - In this paper an algorithm is proposed to extract two illuminant invariant chromaticity features from three image sensor responses. This algorithm extracts these chromaticity features at pixel level therefore it can work well in scenes illuminated with non-uniform illuminant. An approach is proposed to use the algorithm with cameras of unknown sensitivity functions. The algorithm was tested for separability of perceptually similar colours under International Commission on Illumination (CIE) standard illuminants and obtained a good performance. The algorithm was also tested for colour based object recognition by illuminating typical indoor illuminants. The proposed algorithm gives a better performance compared to other existing algorithms investigated. Finally, the algorithm was tested for skin detection invariant to illuminant, ethnic background and imaging device. In this investigation daylight scenes under different weather conditions and scenes illuminated by typical indoor illuminants were used. The proposed algorithm gives a better skin detection performance compared to widely used standard colour spaces. Based on the results presented, the proposed illuminant invariant chromaticity space can be used for machine vision applications including illuminant invariant colour based object recognition and skin detection.

    U2 - 10.1109/TIP.2012.2193135

    DO - 10.1109/TIP.2012.2193135

    M3 - Article

    VL - 21

    SP - 3612

    EP - 3623

    IS - 8

    ER -