Exact matching in image databases

We believe there is a niche for exact sub-image searching in image databases. When only a sub-image is searched for, traditional image searching approaches fail because the sub-image features usually represent only a small fraction of the global image features. Said differently: it is difficult to find the sub-image in the global features. We present a new technique to find sub-images in a (possibly large) image database. The users articulate their interest in a sub-image, i.e. an object within an image, in a so-called precise multi-spot query. We search our spatially oriented color-based image database image-by-image for matches with this multi-spot query.