A Bidirectional Generative Adversarial Network-Based Perceptual Hash Algorithm for Image Content Forensics

被引:0
作者
Ma B. [1 ,2 ]
Wang Y.-L. [1 ,2 ]
Xu J. [3 ]
Wang C.-P. [1 ,2 ]
Li J. [1 ,2 ]
Zhou L.-N. [4 ]
Shi Y.-Q. [5 ]
机构
[1] Department of Computer Science And Technology, Qilu University of Technology, Shandong Academy of Sciences, Jinan
[2] Shandong Provincial Key Laboratory of Computer Network, Jinan
[3] Department of Computer Science And Technology, Shandong University of Finance and Economics, Jinan
[4] Department of Cyber Security, Beijing University of Posts and Telecommunications, Beijing
[5] Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark
来源
Jisuanji Xuebao/Chinese Journal of Computers | 2023年 / 46卷 / 12期
关键词
generative adversarial network; image forensics; mean square error; perceptual hash; skip-connection;
D O I
10.11897/SP.J.1016.2023.02551
中图分类号
学科分类号
摘要
The traditional perceptual hash algorithm creates image perceptual hash code by extracting image features with a pre-designed scheme. As it is hard to make full use of image inherent semantic characters, the performance of perceptual hash code on image content authentication and copyright protection is constrained. In this paper, an unsupervised perceptual hash algorithm for image forensics based on Bidirectional Generative Adversarial Network (BiGAN) is proposed. The main contributions of the paper are as follows:Firstly, depending on the bidirectional iterative adversary among the coding network, the generative network, and the discriminative network, the powerful learning ability of BiGAN on image inherent feature extraction is fully developed;so that the perceptual hash code that has strong image semantic feature representation capability can be created. As a result, both the identification robustness for images with identical content and the discrimination sensitivity for images with different contents are achieved. Hence, the capability of image forensics is improved. Secondly, a BiGAN optimization framework is constructed by adding a skip-connection structure between the coding and the generative network. By concatenating the shallow and deep layers′ features of the sampled image, different dimensional features are organically integrated to improve the learning efficiency and the convergence speed of the proposed scheme. Thereby, the semantic information representation ability of the perceptual hash code is enhanced, and the identification robustness for identical content images is heightened. Thirdly, a Mean Square Error (MSE) loss-based performance optimization strategy for BiGAN is investigated. By computing the difference between the output of the coding network and the generative network, not only the visual quality of the generated image but also the representation capability of the generated perceptual hash code is effectively improved. Consequently, the discrimination sensitivity for different content images is intensified. In the end, by virtue of multiple network iterations and adversarial training, a high-performance perceptual hash code for image forensics is obtained. Furthermore, a large image database CeleA Mask-HQ is employed for the first time to evaluate the performance of the perceptual hash algorithm in this study. The capability of the BiGAN-based perceptual hash algorithm for the identification of images with identical content and for the discrimination of images with different contents is discussed in detail. Meanwhile, both the influence of the skip-connection network structure and that of the mean square error (MSE) loss on the performance improvement of the BiGAN-based perceptual hash algorithm are explored at length. In addition, four excellent image perceptual hash algorithms are involved in the experiment to verify the performance of the proposed scheme in comparisons. Extensive experimental results indicate that the BiGAN-based perceptual hash algorithm gains higher image forensics ability than other state-of-the-art schemes. © 2023 Science Press. All rights reserved.
引用
收藏
页码:2551 / 2572
页数:21
相关论文
共 49 条
[1]  
Ma B, Shi Y Q., A reversible data hiding scheme based on code division multiplexing, IEEE Transactions on Information Forensics and Security, 11, 9, pp. 1914-1927, (2016)
[2]  
Ma B, Chang L, Wang C, Et al., Robust image watermarking using invariant accurate polar harmonic Fourier moments and chaotic mapping, Signal Processing, 172, (2020)
[3]  
Srivastava M, Siddiqui J, Ali M A., Local binary pattern based technique for content based image copy detection, Proceedings of the International Conference on Power Electronics & IoT Applications in Renewable Energy and its Control (PARC), pp. 374-377, (2020)
[4]  
Qin C, Liu E, Feng G, Et al., Perceptual image hashing for content authentication based on convolutional neural network with multiple constraints, IEEE Transactions on Circuits and Systems for Video Technology, 31, 11, pp. 4523-4537, (2020)
[5]  
Donahue J, Krahenbuhl P, Darrell T., Adversarial feature learning, (2016)
[6]  
Schneider M, Chang S F., A robust content based digital signature for image authentication, Proceedings of the 3rd IEEE International Conference on Image Processing, pp. 227-230, (1996)
[7]  
Tang Z, Dai Y, Zhang X, Et al., Perceptual image hashing with histogram of color vector angles, Proceedings of the International Conference on Active Media Technology, pp. 237-246, (2012)
[8]  
Zhao Y, Wang S, Zhang X, Et al., Robust hashing for image authentication using Zernike moments and local features, IEEE Transactions on Information Forensics and Security, 8, 1, pp. 55-63, (2012)
[9]  
Chen Y, Yu W, Feng J., Robust image hashing using invariants of Tchebichef moments, International Journal for Light and Electron Optics, 125, 19, pp. 5582-5587, (2014)
[10]  
Tang Z, Zhang X, Li X, Et al., Robust image hashing with ring partition and invariant vector distance, IEEE Transactions on Information Forensics and Security, 11, 1, pp. 200-214, (2015)