Abstract: A novel perceptual image hashing based on entropies features and Zernike moments has been proposed in this paper.This approach calculates the reference orientation by Zernike moments and the entropies of equal area ring and angle as perceptual features.Then the hash sequence is generated after quantization.The Euclidean distance is used to measure content similarity in the scheme.The experimental results show that the proposed algorithm has good robustness on additive noise,JPEG compression,geometric operations and good discrimination for different images.

Key words: perceptual hashing;entropies features;Zernike moment;robustness,discrimination