Perceptual Image Hashing Method Using Contourlet HMT Model

Abstract

Image hashing finds extensive applications in content authentication, database search. This paper develops a novel algorithm for generating an image hash based on contour let hidden Markov tree (HMT) model and SVD. The contour let transform is a new two-dimensional extension of the wavelet transform using multi scale and directional filter banks. It effectively captures smooth contours that are the dominant feature in natural images. The contour let HMT model can capture all inter-scale, inter-direction, and inter-location dependencies of contour let coefficients using a few statistics parameters. These parameters are stable to content-preserving modifications and at the same time, are sensitive to malicious tampering. We introduce SVD and randomization to produce the hash string. Experimental results show that the proposed hashing methods can provide excellent security and robustness.