Color-based object recognition

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 II, and the newly proposed color models c(1)c(2)c(3) and l(1)l(2)l(3) are all invariant to a change in viewing direction, object geometry and illumination. Further, it is shown that hue H and l(1)l(2)l(3) 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(1)m(2)m(3). 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(1)l(2)l(3) and hue H followed by c(1)c(2)c(3) normalized color rgb and m(1)m(2)m(3) under the constraint of white illumination. Also, it is demonstrated that recognition accuracy degrades substantially for all color features other than m(1)m(2)m(3) With a change in illumination color. The recognition scheme and images are available within the PicToSeek and Pic2Seek systems on-line at: http://www.wins.uva.nl/research/isis/zomax/. (C) 1999 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.