Image indexing using composite color and shape invariant features

New sets of color models are proposed for object recognition invariant to a change in view point, object geometry and illumination. Further, computational methods are presented to combine color and shape invariants to produce a high-dimensional invariant feature set for discriminatory object recognition. Experiments on a database of 500 images show that object recognition based on composite color and shape invariant features provides excellent recognition accuracy. Furthermore, object recognition based on color invariants provides very high recognition accuracy whereas object recognition based entirely on shape invariants yields very poor discriminative power. The image database and the performance of the recognition scheme can be experienced within PicToSeek: on-line as part of the ZOMAX system at: http://www.wins.uva.nl/research/isis/zomax/