Knowing which edges in an image denote shadow edges and which are due to object boundaries or changes in surface reflectance has important applications in both computer vision and mixed reality. We show that the choice of color space has a significant effect on our ability to differentiate shadow edges from reflectance edges, particularly in sunlit scenes. We have evaluated the performance of 11 color spaces on an input data of more than a hundred colors imaged in a variety of illumination conditions. We quantify the performance of these color spaces using receiver operating characteristic curves, and use the z statistic to find if the difference in performances is statistically significant.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Evaluation of color spaces for edge classification in outdoor scenes


    Contributors:
    Khan, E.A. (author) / Reinhard, E. (author)


    Publication date :

    2005-01-01


    Size :

    168907 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Evaluation of Color Spaces for Edge Classification in Outdoor Scenes

    Khan, E. A. / Reinhard, E. | British Library Conference Proceedings | 2005


    Consistent Surface Color for Texturing Large Objects in Outdoor Scenes

    Kawakami, R. / Tan, R. / Ikeuchi, K. et al. | British Library Conference Proceedings | 2005


    2D Matching of 3D Moving Objects in Color Outdoor Scenes

    Dubuisson, M.-P. / Jain, A. K. / Institute of Electrical and Electronics Engineers; Computer Society | British Library Conference Proceedings | 1994


    Consistent surface color for texturing large objects in outdoor scenes

    Kawakami, R. / Ikeuchi, K. / Tan, R.T. | IEEE | 2005


    Use of hyperspectral imagery for material classification in outdoor scenes

    Kwon, H. / Der, S.Z. / Nasrabadi, N.M. et al. | Tema Archive | 1999