In this paper, we concentrate on determining homogeneously colored regions invariant to surface orientation change, illumination, shadows and highlights. To this end, the influence of various well-known color models (e.g. I, RGB, XYZ, I1I2I3, rgb, xyz, UVW, Lab and ISH) are examined, in theory, for the dichromatic reflection model and, in practice, for two distinct region-based segmentation methods: the k-means clustering technique and the split and merge algorithm. Experiments are conducted oncolor images taken from colored objects in real-world scenes. On the basis of the theoretical and experimental results it is concluded that l1l2l3, H, S, c1c2c3, rgb and xyz all detect regions invariant to a change in surface orientation, viewpoint of the camera, and illumination intensity. Furthermore, l1l2l3 and H also detect regions independent of highlights. I, RGB, CMY, YIQ, XYZ, and I1I2I3 provide segmentation results which are all sensitive to surface orientation and illumination intensity as well as color models incorporating brightness into their systems: I in HSI, L* in L*a*b*, and L in Luv.
Keywords:
Color Image Segmentation, Color Spaces, Reflectance Invariant Surface Properties, Kmeans Clustering, Split and Merge Segmentation
