Robust content fingerprinting algorithm based on invariant and hierarchical generative model

摘要

Content fingerprinting has been widely used for protecting the copyright of on-line digital media. By aggregating the perceptual attributes of digital media into an invariant digest, content fingerprinting enables user-generated-contents (UGC) networks to identify the unauthorized distribution of copyrighted contents. In this paper, we propose an image fingerprinting algorithm based on invariant generative model. The proposed work formulates fingerprinting algorithm as a hierarchy of parametric models. For better generalization performance, we first train the models to learn generic visual patterns from local image structures, which is accomplished by fitting the statistical distribution of local patches. The learned models are then fine-tuned to address the robustness and discriminability requirements of content fingerprinting. Moreover, our training scheme also regularizes the norm of gradients to force the models to learn visual features that are insensitive to distortion. The learned models are cascaded with a pooling operation to form the building block of fingerprinting algorithm. Considering the security requirement of copyright protection, we also develop a key-dependent scheme to randomize fingerprint computation. Experimental results validate that the proposed work can withstand a wide variety of distortions and achieve a higher content identification accuracy than competing algorithms. (C) 2018 Elsevier Inc. All rights reserved.