Two-Stage Robust Lossless DWI Watermarking Based on Transformer Networks in the Wavelet Domain
Abstract
:1. Introduction
- (1)
- We propose a two-stage robust lossless DWI watermarking framework based on deep learning in the wavelet domain. Separate branching networks are designed for different frequency bands, which can effectively reduce inter-frequency conflicts and improve the image reconstruction quality and robustness of watermarking.
- (2)
- In the watermark embedding network, we design a frequency-enhanced attention module using both low- and high-frequency information, and this approach effectively integrates multi-frequency features to improve the reconstruction performance.
- (3)
- Compared with other algorithms our proposed algorithm achieves better image reconstruction quality and watermark robustness.
2. Related Works
2.1. Diffusion-Weighted Imaging
2.2. Robust Watermark
2.3. Discrete Wavelet Transform
3. Proposed Method
3.1. Watermark Frame
3.2. Watermark Embedding Network
3.3. Reversible Information Embedding
3.3.1. Difference Image Compression
3.3.2. Integrity Information
3.4. Attack Layer Network
3.5. Watermark Extraction Network
3.6. Image Recovery
3.7. Loss Functions
3.8. Algorithm Process
Algorithm 1 Watermark embedding algorithm. |
Stage1:Training watermark embedding network , watermark extraction network Input: Original DWI image , Original watermark Output: Well-trained , Required model: , , attack layer While epoch<maxepochs:
Input: Original DWI image , Original watermark , Pre-training , Output: Well-trained , Marker Image Required model: , , , Compensation information generation , Reversible embedding While epoch<maxepochs:
|
Algorithm 2 Watermark extraction algorithm. |
Input: Marker Image , Original watermark Output: Watermark , Original DWI image Required model: , Contains watermark test , Copyright Authentication , Integrity Verification , Image Recovery
|
4. Experiments
4.1. Experimental Settings
4.2. Robustness Experiment
4.2.1. No Attack
4.2.2. Common Attacks
4.2.3. Geometric Attacks
4.2.4. Multiple Attacks
4.3. Ablation Experiment
4.4. Comparative Experiment
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Bammer, R. Basic principles of diffusion-weighted imaging. Eur. J. Radiol. 2003, 45, 169–184. [Google Scholar] [CrossRef] [PubMed]
- Zhong, X.; Huang, P.C.; Mastorakis, S.; Shih, F.Y. An automated and robust image watermarking scheme based on deep neural networks. IEEE Trans. Multimed. 2020, 23, 1951–1961. [Google Scholar] [CrossRef]
- Yang, P.; Lao, Y.; Li, P. Robust watermarking for deep neural networks via bi-level optimization. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada, 11–17 October 2021. [Google Scholar]
- Zhang, J.; Chen, D.; Liao, J.; Zhang, W.; Feng, H.; Hua, G.; Yu, N. Deep model intellectual property protection via deep watermarking. IEEE Trans. Pattern Anal. Mach. Intell. 2021, 44, 4005–4020. [Google Scholar] [CrossRef] [PubMed]
- Menendez-Ortiz, A.; Feregrino-Uribe, C.; Hasimoto-Beltran, R.; Garcia-Hernandez, J.J. A survey on reversible watermarking for multimedia content: A robustness overview. IEEE Access 2019, 7, 132662–132681. [Google Scholar] [CrossRef]
- Liu, X.; Lou, J.; Fang, H.; Chen, Y.; Ouyang, P.; Wang, Y.; Zou, B.; Wang, L. A novel robust reversible watermarking scheme for protecting authenticity and integrity of medical images. IEEE Access 2019, 7, 76580–76598. [Google Scholar] [CrossRef]
- Kamil, K.S.; Sahu, M.; K. R., R.; Sahu, A.K. Secure Reversible Data Hiding Using Block-Wise Histogram Shifting. Electronics 2023, 12, 1222. [Google Scholar] [CrossRef]
- Sahu, A.K. A logistic map based blind and fragile watermarking for tamper detection and localization in images. J. Ambient. Intell. Humaniz. Comput. 2022, 13, 3869–3881. [Google Scholar] [CrossRef]
- Coltuc, D. Towards distortion-free robust image authentication. J. Phys. Conf. Ser. 2007, 77, 012005. [Google Scholar] [CrossRef]
- Wang, X.; Li, X.; Pei, Q. Independent embedding domain based two-stage robust reversible watermarking. IEEE Trans. Circuits Syst. Video Technol. 2019, 30, 2406–2417. [Google Scholar] [CrossRef]
- Hu, R.; Xiang, S. Lossless robust image watermarking by using polar harmonic transform. Signal Process. 2021, 179, 107833. [Google Scholar] [CrossRef]
- Hu, R.; Xiang, S. Cover-lossless robust image watermarking against geometric deformations. IEEE Trans. Image Process. 2020, 30, 318–331. [Google Scholar] [CrossRef] [PubMed]
- Zhu, J.; Kaplan, R.; Johnson, J.; Fei-Fei, L. Hidden: Hiding data with deep networks. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018. [Google Scholar]
- Ahmadi, M.; Norouzi, A.; Karimi, N.; Samavi, S.; Emami, A. ReDMark: Framework for residual diffusion watermarking based on deep networks. Expert Syst. Appl. 2020, 146, 113157. [Google Scholar] [CrossRef]
- Luo, X.; Zhan, R.; Chang, H.; Yang, F.; Milanfar, P. Distortion agnostic deep watermarking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 14–19 June 2020. [Google Scholar]
- Liu, Y.; Guo, M.; Zhang, J.; Zhu, Y.; Xie, X. A novel two-stage separable deep learning framework for practical blind watermarking. In Proceedings of the 27th ACM International Conference on Multimedia, Nice, France, 21–25 October 2019. [Google Scholar]
- Fan, B.; Li, Z.; Gao, J. DwiMark: A multiscale robust deep watermarking framework for diffusion-weighted imaging images. Multimed. Syst. 2022, 28, 295–310. [Google Scholar] [CrossRef]
- Chacko, A.; Chacko, S. Deep learning-based robust medical image watermarking exploiting DCT and Harris hawks optimization. Int. J. Intell. Syst. 2022, 37, 4810–4844. [Google Scholar] [CrossRef]
- Dhaya, R. Light weight CNN based robust image watermarking scheme for security. J. Inf. Technol. Digit. World 2021, 3, 118–132. [Google Scholar]
- Chen, Y.P.; Fan, T.Y.; Chao, H.C. Wmnet: A lossless watermarking technique using deep learning for medical image authentication. Electronics 2021, 10, 932. [Google Scholar] [CrossRef]
- Zhang, D.; Zhang, D. Wavelet transform. Fundam. Image Data Mining Anal. Featur. Classif. Retr. 2019, 2019, 35–44. [Google Scholar]
- Stanković, R.S.; Falkowski, B.J. The Haar wavelet transform: Its status and achievements. Comput. Electr. Eng. 2003, 29, 25–44. [Google Scholar] [CrossRef]
- Zamir, S.W.; Arora, A.; Khan, S.; Hayat, M.; Khan, F.S.; Yang, M.H. Restormer: Efficient transformer for high-resolution image restoration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18–24 June 2022; pp. 5728–5739. [Google Scholar]
- Yuan, J.; Zheng, H.; Ni, J. Efficient Reversible Data Hiding Using Two-Dimensional Pixel Clustering. Electronics 2023, 12, 1645. [Google Scholar] [CrossRef]
- Huang, P.; Li, D.; Wang, Y.; Zhao, H.; Deng, W. A Novel Color Image Encryption Algorithm Using Coupled Map Lattice with Polymorphic Mapping. Electronics 2022, 11, 3436. [Google Scholar] [CrossRef]
- Chen, P.; Lei, Y.; Niu, K.; Yang, X. A Novel Separable Scheme for Encryption and Reversible Data Hiding. Electronics 2022, 11, 3505. [Google Scholar] [CrossRef]
- Lee, J.Y.; Kim, C.; Yang, C.N. Reversible Data Hiding Using Inter-Component Prediction in Multiview Video Plus Depth. Electronics 2019, 8, 514. [Google Scholar] [CrossRef] [Green Version]
- Van Essen, D.C.; Ugurbil, K.; Auerbach, E.; Barch, D.; Behrens, T.E.; Bucholz, R.; Chang, A.; Chen, L.; Corbetta, M.; Curtiss, S.W.; et al. The Human Connectome Project: A data acquisition perspective. Neuroimage 2012, 62, 2222–2231. [Google Scholar] [CrossRef] [PubMed] [Green Version]
Model Component | Parameters | Size | Time |
---|---|---|---|
Encoder | 1,864,508 | 7.25 MB | 1.514 s |
Decoder | 3,588,616 | 13.96 MB | 1.128 s |
Total | 5,453,124 | 21.22 MB | 2.642 s |
Images | Avg BER/bit | Avg PSNR/dB |
---|---|---|
64 | 0 | 1 |
Attack Type | Parameter | BER/bit |
---|---|---|
median filtering | K = 3 | 0.000004 |
median filtering | K = 5 | 0.000004 |
median filtering | K = 7 | 0.000016 |
Gaussian filtering | K = 3 | 0.000005 |
Gaussian filtering | K = 5 | 0.00006 |
Gaussian filtering | K = 7 | 0.000081 |
SPN | p = 0.01 | 0.000004 |
SPN | p = 0.02 | 0.000006 |
SPN | p = 0.03 | 0.000006 |
Gaussian noise | v = 0.01 | 0.000004 |
Gaussian noise | v = 0.02 | 0.000385 |
Gaussian noise | v = 0.03 | 0.000013 |
JPEG compression | Q = 90 | 0.000004 |
JPEG compression | Q = 70 | 0.000011 |
JPEG compression | Q = 30 | 0.000005 |
JPEG compression | Q = 10 | 0.002077 |
Attack Type | Parameter | BER/bit |
---|---|---|
rotation | = 5 | 0.000785 |
rotation | = 15 | 0.002837 |
rotation | = 30 | 0.001154 |
rotation | = 45 | 0.001025 |
cropping | q = 0.125 | 0.000004 |
cropping | q = 0.25 | 0.000004 |
cropping | q = 0.5 | 0.000004 |
cropping | q = 0.7 | 0.000004 |
scaling | r = 0.5 | 0.000003 |
scaling | r = 0.75 | 0.000004 |
scaling | r = 1.25 | 0.000003 |
scaling | r = 1.5 | 0.000004 |
scaling | r = 2 | 0.000004 |
Attack1 | Attack2 | Attack3 | BER/bit |
---|---|---|---|
MF K = 7 | GN v = 0.03 | scaling r = 0.5 | 0.0003 |
GF K = 5 | rotation = 45 | JPEG Q = 30 | 0.0632 |
GF K = 3 | cropping q = 0.125 | JPEG Q = 90 | 0.0011 |
SPN p = 0.02 | cropping q = 0.25 | JPEG Q = 70 | 0.0756 |
MF K = 5 | GN v = 0.01 | JPEG Q = 30 | 0.0504 |
SPN p = 0.02 | rotation = 30 | JPEG Q = 30 | 0.0876 |
No. | LHFA Block | Avg PSNR/dB |
---|---|---|
1 | ✓ | 60.18 |
2 | ✕ | 58.43 |
Watermarked Image | [13] | [17] | [10] | [11] | [12] | Proposed |
---|---|---|---|---|---|---|
PSNR/dB | 39.08 | 58.69 | 43.7 | 43.1 | 46.8 | 60.18 |
Attack | [13] | [17] | [10] | [11] | [12] | Proposed |
---|---|---|---|---|---|---|
GN (0.01) | 0.002 | 0.000 | 0.000 | 0.010 | 0.000 | 0.000 |
GN (0.02) | 0.024 | 0.000 | 0.000 | 0.060 | 0.010 | 0.000 |
GN (0.03) | 0.025 | 0.026 | 0.000 | 0.180 | 0.050 | 0.000 |
JPEG (90) | 0.164 | 0.000 | 0.000 | 0.000 | 0.000 | 0.000 |
JPEG (70) | 0.333 | 0.012 | 0.000 | 0.000 | 0.000 | 0.000 |
JPEG (30) | 0.394 | 0.343 | 0.000 | 0.000 | 0.000 | 0.000 |
JPEG (10) | 0.430 | 0.375 | 0.150 | 0.000 | 0.000 | 0.002 |
rotation (5) | 0.004 | 0.000 | — | 0.000 | 0.000 | 0.000 |
rotation (15) | 0.009 | 0.010 | — | 0.000 | 0.000 | 0.002 |
rotation (30) | 0.011 | 0.010 | — | 0.000 | 0.000 | 0.001 |
rotation (45) | 0.011 | 0.020 | — | 0.000 | 0.000 | 0.001 |
scaling (0.5) | 0.063 | 0.001 | — | 0.000 | 0.000 | 0.000 |
scaling (0.75) | 0.096 | 0.010 | — | 0.006 | 0.002 | 0.000 |
scaling (1.25) | 0.131 | 0.010 | — | 0.000 | 0.000 | 0.000 |
scaling (1.5) | 0.150 | 0.015 | — | 0.000 | 0.030 | 0.000 |
scaling (2) | 0.206 | 0.025 | — | 0.020 | 0.010 | 0.000 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Liu, Z.; Li, Z.; Zheng, L.; Li, D. Two-Stage Robust Lossless DWI Watermarking Based on Transformer Networks in the Wavelet Domain. Appl. Sci. 2023, 13, 6886. https://doi.org/10.3390/app13126886
Liu Z, Li Z, Zheng L, Li D. Two-Stage Robust Lossless DWI Watermarking Based on Transformer Networks in the Wavelet Domain. Applied Sciences. 2023; 13(12):6886. https://doi.org/10.3390/app13126886
Chicago/Turabian StyleLiu, Zhangyu, Zhi Li, Long Zheng, and Dandan Li. 2023. "Two-Stage Robust Lossless DWI Watermarking Based on Transformer Networks in the Wavelet Domain" Applied Sciences 13, no. 12: 6886. https://doi.org/10.3390/app13126886
APA StyleLiu, Z., Li, Z., Zheng, L., & Li, D. (2023). Two-Stage Robust Lossless DWI Watermarking Based on Transformer Networks in the Wavelet Domain. Applied Sciences, 13(12), 6886. https://doi.org/10.3390/app13126886