A Novel Robust Image-Hashing Method for Content Authentication

Abstract

Image hash functions find extensive application in content authentication, database search, and digital forensic. This paper develops a novel robust image-hashing method based on genetic algorithm (GA) and Back Propagation (BP) Neural Network for content authentication. Lifting wavelet transform is used to extract image low frequency coefficients to create the image feature matrix. A GA-BP network model is constructed to generate image-hashing code. Experimental results demonstrate that the proposed hashing method is robust against random attack, JPEG compression, additive Gaussian noise, and so on. Receiver operating characteristics (ROC) analysis over a large image database reveals that the proposed method significantly outperforms other approaches for robust image hashing.