A Novel Image Perceptual Hashing Algorithm via Feature Points and Fuzzy Distance Matching

A novel image perceptual hashing algorithm is proposed on the intermediate hashing stage. It first uses an iterative geometric technique to extract significant geometry preserving feature points. Then, the fuzzy distance matching method is proposed based on the observation that the distances of feature points are invariant in the polar coordinate under arbitrary rotation. It is verified that the proposed perceptual hashing method can withstand standard benchmark (e.g. Stirmark) attacks including compression and image enhancement. Especially, although most methods based on low-level image feature extraction approaches only have the rotation robustness not more than 5 degrees, the proposed method have a very strong robustness under arbitrary rotation attacks. Moreover, the fuzzy distance matching method can be applied to any low-level image feature extraction approaches as well to improve their rotation robustness.