Finding near-duplicate images on the web using fingerprints
Srinitish Srinivasan, Neela Sawant · 2008
The traditional near-duplicate detection systems developed for digital photo management and copyright protection are not applicable for the de-duplication of large-scale web image corpus. In this paper, we present a fast, accurate and highly scalable image fingerprinting technique suited for near-duplicate detection at the web-scale. The image fingerprint is a compact 130 bit representation computed using Fourier-Mellin transform. Near-duplicate images are detected in O(1) time using fingerprint equality and is faster than fast approximate near-neighbor searches like LSH.