A skin-color extraction algorithm is proposed to detect human faces in color images with varying illumination condition and presence of complex background. The approach is based on both a Gaussian mixture model of human skin-color distribution and image segmentation using all automatic and adaptive multi-thresholding technique. Detected regions are then refined by morphological operations. Experimental results on images presenting a wide range of variations in lighting condition, face orientation, scale, pose, facial expression and background, demonstrate the efficiency of our skin-segmentation algorithm. Using additional information about facial features, our method becomes an efficient step in localizing candidate faces for a face detection system.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Skin-color extraction in images with complex background and varying illumination


    Contributors:
    Quan Huynh-Thu, (author) / Meguro, M. (author) / Kaneko, M. (author)


    Publication date :

    2002-01-01


    Size :

    595006 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Skin-Color Extraction in Images with Complex Background and Varying Illumination

    Huynh-Thu, Q. / Meguro, M. / Kaneko, M. et al. | British Library Conference Proceedings | 2002


    Illumination Invariant Background Extraction

    Durucan, E. / Snoeckx, J. / Weilenmann, Y. et al. | British Library Conference Proceedings | 1999


    Color Constancy under Varying Illumination

    Finlayson, G. / Funt, B. / Barnard, K. et al. | British Library Conference Proceedings | 1995


    Comparison of skin color detection and tracking methods under varying illumination

    Martinkauppi, B. / Soriano, M. / Pietikainen, M. | British Library Online Contents | 2005


    Color Constancy for Scenes with Varying Illumination

    Barnard, K. / Finlayson, G. / Funt, B. | British Library Online Contents | 1997