On the separation of luminance from colour in images

Many computer vision and graphics related techniques rely upon illumination invariance of images to derive meaning from images of an object under varying lighting conditions. This is all the appearance-based methods. In practice however this assumption does not hold if one is not careful with either controlling the illumination of the object when capturing its appearance or with some post-processing of the images. This paper presents results of experiments designed to analyse the usefulness for illumination invariance of two colour models, CIE L*a*b* and YUV, that have been designed to provide separation of the luminance information from the colour information, and compare them with more traditional colour models, RGB and HSV. This is done by evaluating the variations in each of the components of the different colour spaces in real images taken in variable illumination conditions. We also present a simple application example.