Binary multi-view perceptual hashing for image authentication

Abstract

This paper presents a novel Binary Multi-View Perceptual Hashing (BMVPH) scheme for image authentication, which provides compact and efficient representations and can easily scale to large data. We apply virtual prior attacks (e.g. additive noise, blurring, compression, logo-insert etc.) on original images to generate simulated distorted copies. The original images and the corresponding distorted copies provide the so-called training set. For perceptual hashing learning, we formulate BMVPH by two key components: collaborative binary representation learning (CBRL) and perpetual content authentication learning (PCAL), into a unified learning framework. Our BMVPH scheme collaboratively encodes the multi-view features into a compact common binary code space while considering the perceptual content similarity at the same time. The experimental results show that when compared with the state-of-the-art methods, the proposed algorithm can achieve higher discrimination and better perceptual robustness. In particular, the Area Under ROC Curve (AUC) increases on average of 3.8% as compared with other state-of-the-art methods.