A batch copyright scheme for digital image based on deep neural network

Haoyu Lu; Daofu Gong; Fenlin Liu; Hui Liu; Jinghua Qu; Haoyu Lu; Daofu Gong; Fenlin Liu; Hui Liu; Jinghua Qu

doi:10.3934/mbe.2019306

Mathematical Biosciences and Engineering

2019, Volume 16, Issue 5: 6121-6133. doi: 10.3934/mbe.2019306

Previous Article Next Article

Research article Special Issues

A batch copyright scheme for digital image based on deep neural network

1.
Zhengzhou Science and Technology Institute, Zhengzhou, 450001, China
2.
University of Surrey, Guildford, Surrey, GU2 7XH, UK

Received: 15 January 2019 Accepted: 08 April 2019 Published: 03 July 2019

Digital signature and watermarking are effective image copyright protection techniques. However, these methods come with some inherent drawbacks, including the incapacity of carrying information and inevitable fidelity loss, respectively. To improve this situation, this paper proposes a neural network-based image batch copyright protection scheme, with which a copyright message bitstream can be extracted from each registered image while no modifications are introduced. Taking advantage of the pattern extraction capability and the error tolerance of the neural network, the proposed scheme achieves perfect imperceptibility and superior robustness. Moreover, the network's preference for diverse data content makes it especially appropriate for multiple images copyright verification. These claims will be further supported by the experimental results in this paper.
- digital image,
- copyright protection,
- deep neural network,
- robust feature extraction,
- digital watermarking
Citation: Haoyu Lu, Daofu Gong, Fenlin Liu, Hui Liu, Jinghua Qu. A batch copyright scheme for digital image based on deep neural network[J]. Mathematical Biosciences and Engineering, 2019, 16(5): 6121-6133. doi: 10.3934/mbe.2019306

Related Papers:

Abstract

Digital signature and watermarking are effective image copyright protection techniques. However, these methods come with some inherent drawbacks, including the incapacity of carrying information and inevitable fidelity loss, respectively. To improve this situation, this paper proposes a neural network-based image batch copyright protection scheme, with which a copyright message bitstream can be extracted from each registered image while no modifications are introduced. Taking advantage of the pattern extraction capability and the error tolerance of the neural network, the proposed scheme achieves perfect imperceptibility and superior robustness. Moreover, the network's preference for diverse data content makes it especially appropriate for multiple images copyright verification. These claims will be further supported by the experimental results in this paper.

References

[1]	G. L. Friedman, The trustworthy digital camera: Restoring credibility to the photographic image, IEEE T. Consum. Elec., 39 (1993), 905–910.
[2]	S. Bhattacharjee and M. Kutter, Compression tolerant image authentication, International Conference on Image Processing, (1998), 435–439.
[3]	J. Dittmann, A. Steinmetz and R. Steinmetz, Content-based digital signature for motion pictures authentication and content-fragile watermarking, IEEE International Conference on Multimedia Computing and Systems, (1999), 209–213.
[4]	C. Lin and S. Chang, Robust image authentication method surviving jpeg lossy compression, Storage and Retrieval for Image and Video Databases VI. International Society for Optics and Photonics, 3312 (1997), 296–308.
[5]	C. S. Lu and H. Liao, Structural digital signature for image authentication: an incidental distortion resistant scheme, IEEE T. Multimedia, 5 (2003), 161–173.
[6]	D. Gong, F. Liu and X. Luo, An image edge based robust watermarking algorithm, Sci. Sin. Inform., 43 (2013), 1410–1430.
[7]	H. Qi, D. Zheng and J. Zhao, Human visual system based adaptive digital image watermarking, Sig. Proc., 88 (2008), 174–188.
[8]	J. Seo and C. Yoo, Image watermarking based on invariant regions of scale-space representation, IEEE T. Sig. Proc., 54 (2006), 1537–1549.
[9]	Y. Wang, R. Ni, Y. Zhao, et al., Watermark embedding for direct binary searched halftone images by adopting visual cryptography, Comput. Mater. Continua, 55 (2018), 255–265.
[10]	J. Tsai, W. Huang, C. Chen, et al., A feature-based digital image watermarking for copyright protection and content authentication, IEEE International Conference on Image Processing, 5 (2007), V–469.
[11]	Y. Zhang, D. Ye, J. Gan, et al., An image steganography algorithm based on quantization index modulation resisting scaling attacks and statistical detection, Comput. Mater. Continua, 56 (2018), 151–167.
[12]	Y. Lin, C. Huang and G. Lee, Rotation, scaling, and translation resilient watermarking for images, IET Image Proc., 5 (2011), 328–340.
[13]	J. Tsai, W. Huang, Y. Kuo, et al., On the selection of optimal feature region set for robust digital image watermarking, IEEE T. Image Proc., 20 (2011), 735–743.
[14]	M. Kutter, F. Jordan, F. Bossen, et al., Digital watermarking of color images using amplitude modulation, J. Elec. Imaging, 7 (1998), 326–333.
[15]	D. Gong, Y. Chen, H. Lu, et al., Self-embedding image watermarking based on combined decision using pre-offset and post-offset blocks, Comput. Mater. Continua, 57 (2018), 243–260.
[16]	T. Sridevi, T. Ramya, Y. Ramadevi, et al., A robust watermarking algorithm based on image normalization, in 2010 Second Vaagdevi International Conference on Information Technology for Real World Problems (VCON), (2010), 70–75.
[17]	K. Liu, Wavelet-based watermarking for color images through visual masking, AEU-Int. J. Electron. C., 64 (2010), 112–124.
[18]	N. Kalantari, S. M. Ahadi and M. Vafadust, A robust image watermarking in the ridgelet domain using universally optimum decoder, IEEE T. Circ. Syst. Vid., 20 (2010), 396–406.
[19]	C. Lin, M. Wu, J. Bloom, et al., Rotation, scale, and translation resilient watermarking for images, IEEE T. Image Proc., 10 (2001), 767–782.
[20]	X. Kang, J. Huang, Jiwu, Y. Shi, et al., A dwt-dft composite watermarking scheme robust to both affine transform and jpeg compression, IEEE T. Circ. Syst. Vid., 13 (2003), 776–786.
[21]	X. Kang, J. Huang and W. Zeng, Efficient general print-scanning resilient data hiding based on uniform log-polar mapping, IEEE T. Inf. Foren. Sec., 5 (2010), 1–12.
[22]	D. Rosiyadi, S. Horng, P. Fan, et al., Copyright protection for e-government document images, IEEE MultiMedia, 19 (2012), 62–73.
[23]	I. Cox, M. Miller, J. Bloom, et al., in Digital watermarking and steganography, Morgan kaufmann, (2007).
[24]	H. Al-Otum and A. Al-Taba'a, Adaptive color image watermarking based on a modified improved pixel-wise masking technique, Comput. Electr. Eng., 35 (2009), 673–695.
[25]	H. Song, S. Yu, X. Yang, et al., Contourlet-based image adaptive watermarking, Sig. Proc. Image Comm., 23 (2008), 162–178.
[26]	L. Ma, D. Yu, G. Wei, et al., Adaptive spread-transform dither modulation using a new perceptual model for color image watermarking, IEICE T. Inf. Sys., 93 (2010), 843–857.
[27]	C. Song, S. Sudirman and M. Merabti, Robust digital image watermarking using region adaptive embedding technique, 2010 IEEE International Conference on Progress in Informatics and Computing (PIC), 1 (2010), 378–382.
[28]	L. Wu, Y. Wang, J. Gao, et al., Deep adaptive feature embedding with local sample distributions for person re-identification, Pat. Recog., 73 (2018), 275–288.
[29]	L. Wu, Y. Wang, X. Li, et al., What-and-where to match: deep spatially multiplicative integration networks for person re-identification, Pat. Recog., 76 (2018), 727–738.
[30]	L. Wu, Y. Wang, J. Gao, et al., Where-and-when to look: Deep siamese attention networks for video-based person re-identification, IEEE T. Multimedia, 21 (2019), 1412–1424.
[31]	G. Cybenko, Approximation by superpositions of a sigmoidal function, Math. Control Signal., 2 (1989), 303–314.
[32]	K. Hornik, M. Stinchcombe and H. White, Multilayer feedforward networks are universal approximators, Neural Networks, 2 (1989), 359–366.

Reader Comments

Your name:*

Email:*
© 2019 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)