Color-based object recognition

Abstract

The purpose is to arrive at recognition of multicolored objects invariant to a substantial change in viewpoint, object geometry and illumination. Assuming dichromatic reflectance and white illumination, it is shown that normalized color rgb, saturation S and hue H, and the newly proposed color models c � c � c � and l � l � l � are all invariant to a change in viewing direction, object geometry and illumination. Further, it is shown that hue H and l � l � l � are also invariant to highlights. Finally, a change in spectral power distribution of the illumination is considered to propose a new color constant color model m � m � m �. To evaluate the recognition accuracy differentiated for the various color models, experiments have been carried out on a database consisting of 500 images taken from 3-D multicolored man-made objects. The experimental results show that highest object recognition accuracy is achieved by l � l � l � and hue H followed by c � c � c � , normalized color rgb and m � m � m � under the constraint of white illumination. Also, it is demonstrated that recognition accuracy degrades substantially for all color features other than m � m � m � with a change in illumination color. The recognition scheme and images are available within the PicToSeek and Pic2Seek systems on-line at: