Evaluation of color descriptors for object and scene recognition

Image category recognition is important to access visual information on the level of objects and scene types. So far, intensity-based descriptors have been widely used. To in- crease illumination invariance and discriminative power, color descriptors have been proposed only recently. As many descriptors exist, a structured overview of color in- variant descriptors in the context of image category recog- nition is required. Therefore, this paper studies the invariance properties and the distinctiveness of color descriptors in a structured way. The invariance properties of color descriptors are shown analytically using a taxonomy based on invariance properties with respect to photometric transformations. The distinctiveness of color descriptors is assessed experimen- tally using two benchmarks from the image domain and the video domain. From the theoretical and experimental results, it can be derived that invariance to light intensity changes and light color changes affects category recognition. The results re- veal further that, for light intensity changes, the usefulness of invariance is category-specific.