We describe an algorithm for computing an image signature, suitable for first-stage screening for duplicate images. Our signature relies on relative brightness of image regions, and is generally applicable to photographs, text documents, and line art. We give experimental results on the sensitivity and robustnessof signatures for actual imagecollections, and also results on the robustness of signatures under transformations such as resizing, rescanning, and compression.
Chi Wong, Marshall W. Bern, David Goldberg