Perceptual image hash for tampering detection using Zernike moments

In this paper, a new image hashing method using Zernike moments is proposed. This method is based on rotation invariance of magnitudes and corrected phases of Zernike moments. At first the input image is divided into overlapped blocks. Zernike moments of these blocks are calculated and then each of the amplitudes and phases of modified Zernike moments is then encoded into three bits to form the intermediate hash. Lastly, the final hash sequence is obtained by pseudo-randomly permuting the intermediate hash sequence. Similarity between hashes is measured with the Hamming distance. Experimental results show that this method is robust against most content-preserving attacks. The Hamming distance of Hashes between two different images is bigger than the threshold. This method can be used to detect tampering image, and can locate the tampered region in the image.