Joint Fingerprinting and Decryption for VQ Images through Bipartite Matching

The legality of redistribution of digital content over the Internet has become critical in commerce. The goal of the traitor tracing problem is to find out the traitor who illegally distributes the digital content. In this paper, a joint fingerprinting and decryption (JFD) scheme based on vector quantization and bipartite matching for traitor tracing is proposed. Before transmission, the proposed method encrypts the VQ compressed image through bipartite graphs. After the receiver performs decryption and fingerprinting, the recover image containing user´s fingerprint is only slightly different from the original one and can be used for traitor tracing. The experimental results show that the encrypted image possesses unintelligibility and the recovered image has desirable image quality greatly related to the codebook size.