Coloring image search with coupled multi-index

The precision of visual matching and the trade-off between accuracy and time efficiency have long been bottlenecks of image search systems. This work addresses the two problem simultaneously by introducing the coupled Multi-Index (cMI) structure. First, by combining SIFT and color features on the indexing-level, the discriminative power of visual words is greatly enhanced. Second, by reducing the number of inverted entries to be traversed, c-MI brings about significant improvement in time efficiency. Experiments are performed on two widely used benchmark datasets. We demonstrate both state-of-the-art image search accuracy and cut-by-half query time.