ROBUST COLOR IMAGE WATERMARKING BASED ON DWT AND CNN
Article Sidebar
-
Watermarking, Copyright Protection, DWT, CNN, U-Net
Abstract
Digital watermarking is one of the most important technologies used today for copyright protection and authentication as well as data security in the digital domain. While many existing techniques perform well under certain conditions, designing a method that is both imperceptible and robust against various attacks remains a key challenge, especially for color images. This paper proposes robust color image watermarking based on Discrete Wavelet Transform (DWT) and Convolutional Neural Networks (CNNs). The method incorporates a U-Net architecture enhanced with Squeeze-and-Excitation (SE) blocks and residual learning. The watermark is embedded in the High-Low (HL1) sub-band of the blue-difference chrominance (Cb) channel in YCbCr color space leveraging its lower perceptual sensitivity. A parallel extraction network is jointly trained using a hybrid loss function combining Mean Squared Error (MSE) and Structural Similarity Index (SSIM) to ensure visual quality and extraction reliability. The experiment conducted on the COCO2017 dataset thus shows that the proposed method can achieve a good of imperceptibility with PSNR reaching 45.35 dB and SSIM attaining 0.996. Moreover, it can demonstrate against a variety of attacks such as noise, compression, filtering, rotation, and cropping
Full text article
References
Abdallah, E. E., Ben Hamza, A., & Bhattacharya, P. (2009). Watermarking 3D models using spectral mesh compression. Signal, image and video processing, 3(4), 375-389. DOI: https://doi.org/10.1007/s11760-008-0079-y.
Abdullatif, M., Khalifa, O. O., Olanrewaju, R. F., & Zeki, A. M. (2014, September). Robust image watermarking scheme by discrete wavelet transform. In 2014 International Conference on Computer and Communication Engineering (pp. 316-319). IEEE. DOI: 10.1109/ICCCE.2014.95.
Aberna, P., & Agilandeeswari, L. (2024). Digital image and video watermarking: methodologies, attacks, applications, and future directions. Multimedia Tools and Applications, 83(2), 5531-5591.DOI: https://doi.org/10.1007/s11042-023-15806-y.
Abraham, J., & Paul, V. (2019). An imperceptible spatial domain color image watermarking scheme. Journal of King Saud University-Computer and Information Sciences, 31(1), 125-133. DOI: https://doi.org/10.1016/j.jksuci.2016.12.004.
Ahmadi, M., Norouzi, A., Karimi, N., Samavi, S., & ReDMark, A. E. (2019). Framework for residual diffusion watermarking based on deep networks., 2020, 146. DOI: https://doi. org/10.1016/j. eswa, 113157.
Ben Jabra, S., & Ben Farah, M. (2024). Deep learning-based watermarking techniques challenges: a review of current and future trends. Circuits, Systems, and Signal Processing, 43(7), 4339-4368. DOI: https://doi.org/10.1007/s00034-024-02651-z.
Benoraira, A., Benmahammed, K., & Boucenna, N. (2015). Blind image watermarking technique based on differential embedding in DWT and DCT domains. EURASIP Journal on Advances in Signal Processing, 2015(1), 55.DOI: https://doi.org/10.1186/s13634-015-0239-5.
Boujerfaoui, S., Riad, R., Douzi, H., Ros, F., & Harba, R. (2022). Image watermarking between conventional and learning-based techniques: a literature review. Electronics, 12(1), 74. DOI: https://doi.org/10.3390/electronics12010074.
Chopra, J., Kumar, A., Aggarwal, A. K., & Marwaha, A. (2018, February). An efficient watermarking for protecting signature biometric template. In 2018 5th international conference on signal processing and integrated networks (SPIN) (pp. 413-418). IEEE. DOI: 10.1109/SPIN.2018.8474269.
Darwish, M. M., Farhat, A. A., & El-Gindy, T. M. (2024). Convolutional neural network and 2D logistic-adjusted-Chebyshev-based zero-watermarking of color images. Multimedia Tools and Applications, 83(10), 29969-29995. DOI: https://doi.org/10.1007/s11042-023-16649-3.
Giri, K. J., Quadri, S. M. K., Bashir, R., & Bhat, J. I. (2020). DWT based color image watermarking: a review. Multimedia Tools and Applications, 79(43), 32881-32895. DOI: https://doi.org/10.1007/s11042-020-09716-6.
Gull, S., & Parah, S. A. (2024). Advances in medical image watermarking: a state of the art review. Multimedia Tools and Applications, 83(1), 1407-1447.DOI: https://doi.org/10.1007/s11042-023-15396-9.
Guo, Y., Li, B. Z., & Goel, N. (2017). Optimised blind image watermarking method based on firefly algorithm in DWT‐QR transform domain. IET Image processing, 11(6), 406-415.DOI: https://doi.org/10.1049/iet-ipr.2016.0515.
Hosny, K. M., Magdi, A., ElKomy, O., & Hamza, H. M. (2024). Digital image watermarking using deep learning: A survey. Computer Science Review, 53, 100662. DOI: https://doi.org/10.1016/j.cosrev.2024.100662.
Hsu, L. Y., & Hu, H. T. (2021). QDCT-based blind color image watermarking with aid of GWO and DnCNN for performance improvement. IEEE Access, 9, 155138-155152. DOI: 10.1109/ACCESS.2021.3127917
Huang, Y., Niu, B., Guan, H., & Zhang, S. (2019). Enhancing image watermarking with adaptive embedding parameter and PSNR guarantee. IEEE Transactions on Multimedia, 21(10), 2447-2460.DOI:10.1109/TMM.2019.2907475.
Jaiswal, S., & Pandey, M. K. (2023, February). Deep artificial neural network based blind color image watermarking. In Doctoral Symposium on Human Centered Computing (pp. 101-112). Singapore: Springer Nature Singapore. DOI: https://doi.org/10.1007/978-981-99-3478-2_10.
Jamali, M., Karimi, N., Khadivi, P., Shirani, S., & Samavi, S. (2023). Robust watermarking using diffusion of logo into auto-encoder feature maps. Multimedia Tools and Applications, 82(29), 45175-45201. DOI: https://doi.org/10.1007/s11042-023-15371-4.
Juarez-Sandoval, O. U., Garcia-Ugalde, F. J., Cedillo-Hernandez, M., Ramirez-Hernandez, J., & Hernandez-Gonzalez, L. (2021). Imperceptible–visible watermarking to information security tasks in color imaging. Mathematics, 9(19), 2374.DOI: https://doi.org/10.3390/math9192374.
Kandi, H., Mishra, D., & Gorthi, S. R. S. (2017). Exploring the learning capabilities of convolutional neural networks for robust image watermarking. Computers & Security, 65, 247-268. DOI: https://doi.org/10.1016/j.cose.2016.11.016.
Kang, X. B., Zhao, F., Lin, G. F., & Chen, Y. J. (2018). A novel hybrid of DCT and SVD in DWT domain for robust and invisible blind image watermarking with optimal embedding strength. Multimedia Tools and Applications, 77(11), 13197-13224. DOI: https://doi.org/10.1007/s11042-017-4941-1.
Kumar, S., & Singh, B. K. (2021). DWT based color image watermarking using maximum entropy. Multimedia Tools and Applications, 80(10), 15487-15510. DOI: https://doi.org/10.1007/s11042-020-10322-9.
Lee, J. E., Seo, Y. H., & Kim, D. W. (2020). Convolutional neural network-based digital image watermarking adaptive to the resolution of image and watermark. Applied Sciences, 10(19), 6854. DOI: https://doi.org/10.3390/app10196854.
Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., ... & Zitnick, C. L. (2014, September). Microsoft coco: Common objects in context. In European conference on computer vision (pp. 740-755). Cham: Springer International Publishing. DOI: https://doi.org/10.1007/978-3-319-10602-1_48.
Liu, Y., Guo, M., Zhang, J., Zhu, Y., & Xie, X. (2019, October). A novel two-stage separable deep learning framework for practical blind watermarking. In Proceedings of the 27th ACM International conference on multimedia (pp. 1509-1517) DOI: https://doi.org/10.1145/3343031.3351025.
Lu, J., Ni, J., Su, W., & Xie, H. (2022, July). Wavelet-based CNN for robust and high-capacity image watermarking. In 2022 IEEE International Conference on Multimedia and Expo (ICME) (pp. 1-6). IEEE.DOI: 10.1109/ICME52920.2022.9859725.
Luo, X., Zhan, R., Chang, H., Yang, F., & Milanfar, P. (2020). Distortion agnostic deep watermarking. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 13548-13557).DOI: https://doi.org/10.48550/arXiv.2001.04580.
Luo, Y., Tan, X., & Cai, Z. (2024). Robust Deep Image Watermarking: A Survey. Computers, Materials & Continua, 81(1). DOI: 10.32604/cmc.2024.055150.
Ma, L., Fang, H., Wei, T., Yang, Z., Ma, Z., Zhang, W., & Yu, N. (2024, September). A Geometric Distortion Immunized Deep Watermarking Framework with Robustness Generalizability. In European Conference on Computer Vision (pp. 268-285). Cham: Springer Nature Switzerland. DOI: https://doi.org/10.1007/ 978-3-031-72855-6_16.
Mahapatra, D., Amrit, P., Singh, O. P., Singh, A. K., & Agrawal, A. K. (2023). Autoencoder-convolutional neural network-based embedding and extraction model for image watermarking. Journal of Electronic Imaging, 32(2), 021604-021604. DOI: https://doi.org/10.1117/1.JEI.32.2.021604.
Mahto, D. K., Anand, A., & Singh, A. K. (2022). Hybrid optimisation-based robust watermarking using denoising convolutional neural network. Soft Computing, 26(16), 8105-8116.DOI: https://doi.org/10.1007/s00500-022-07155-z.
Mohammed, A. O., Hussein, H. I., Mstafa, R. J., & Abdulazeez, A. M. (2023). A blind and robust color image watermarking scheme based on DCT and DWT domains. Multimedia Tools and Applications, 82(21), 32855-32881. DOI: https://doi.org/10.1007/s11042-023-14797-0.
Mousavi, S. M., Naghsh, A., & Abu-Bakar, S. A. R. (2014). Watermarking techniques used in medical images: a survey. Journal of digital imaging, 27(6), 714-729.DOI: https://doi.org/10.1007/s10278-014-9700-5.
Mstafa, R. J. (2025). Reversible video steganography using quick response codes and modified elgamal cryptosystem. arXiv preprint arXiv:2508.07289.. DOI: 10.32604/cmc.2022.025791.
Padhi, S. K., Tiwari, A., & Ali, S. S. (2024). Deep Learning-based Dual Watermarking for Image Copyright Protection and Authentication. IEEE Transactions on Artificial Intelligence. DOI: 10.1109/TAI.2024.3485519.
Rai, M., Goyal, S., & Pawar, M. (2023). An optimized deep fusion convolutional neural network-based digital color image watermarking scheme for copyright protection. Circuits, Systems, and Signal Processing, 42(7), 4019-4050. DOI: https://doi.org/10.1007/s00034-023-02299-1.
Rajani, D., & Kumar, P. R. (2020). An optimized blind watermarking scheme based on principal component analysis in redundant discrete wavelet domain. Signal Processing, 172, 107556. DOI: https://doi.org/10.1016/j.sigpro.2020.107556.
Rouhani, B. D., Chen, H., & Koushanfar, F. (2019, April). Deepsigns: an end-to-end watermarking framework for protecting the ownership of deep neural networks. In ACM International Conference on Architectural Support for Programming Languages and Operating Systems (Vol. 3, p. 1). DOI: https://doi.org/10.1145/3297858.3304051.
Singh, D., & Singh, S. K. (2017). DWT-SVD and DCT based robust and blind watermarking scheme for copyright protection. Multimedia Tools and Applications, 76(11), 13001-13024. DOI: https://doi.org/10.1007/s11042-016-3706-6.
Singh, R., Saraswat, M., Ashok, A., Mittal, H., Tripathi, A., Pandey, A. C., & Pal, R. (2023). From classical to soft computing based watermarking techniques: A comprehensive review. Future Generation Computer Systems, 141, 738-754. DOI: https://doi.org/10.1016/j.future.2022.12.015.
Sinhal, R., Jain, D. K., & Ansari, I. A. (2021). Machine learning based blind color image watermarking scheme for copyright protection. Pattern Recognition Letters, 145, 171-177. DOI: https://doi.org/10.1016/j.patrec.2021.02.011.
Subramanian, N., Cheheb, I., Elharrouss, O., Al-Maadeed, S., & Bouridane, A. (2021). End-to-end image steganography using deep convolutional autoencoders. IEEE Access, 9, 135585-135593. DOI:10.1109/ACCESS.2021.3113953.
Sy, N. C., Kha, H. H., & Hoang, N. M. (2020). An efficient robust blind watermarking method based on convolution neural networks in wavelet transform domain. Int. J. Mach. Learn. Comput, 10, 675-684. DOI: 10.18178/ijmlc.2020.10.5.990
Tavakoli, A., Honjani, Z., & Sajedi, H. (2023). Convolutional neural network-based image watermarking using discrete wavelet transform. International Journal of Information Technology, 15(4), 2021-2029. DOI: https://doi.org/10.1007/s41870-023-01232-8.
Thakral, S., & Manhas, P. (2018, July). Image processing by using different types of discrete wavelet transform. In International Conference on Advanced Informatics for Computing Research (pp. 499-507). Singapore: Springer Singapore..DOI: https://doi.org/10.1007/978-981-13-3140-4_45.
Yasmeen, F., & Uddin, M. S. (2021). An efficient watermarking approach based on LL and HH edges of DWT–SVD. SN Computer Science, 2(2), 82. DOI: https://doi.org/10.1007/s42979-021-00478-y.
Ye, G., Gao, J., Yin, B., Xie, W., & Wei, X. (2023, October). Deep boosting robustness of DNN-based image watermarking via Dbmark. In 2023 International Conference on Culture-Oriented Science and Technology (CoST) (pp. 186-191). IEEE. DOI: 10.1109/CoST60524.2023.00046.
Zear, A., Singh, A. K., & Kumar, P. (2018). A proposed secure multiple watermarking technique based on DWT, DCT and SVD for application in medicine. Multimedia tools and applications, 77(4), 4863-4882.DOI: https://doi.org/10.1007/s11042-016-3862-8 .
Zermi, N., Khaldi, A., Kafi, R., Kahlessenane, F., & Euschi, S. (2021). A DWT-SVD based robust digital watermarking for medical image security. Forensic science international, 320, 110691.DOI: https://doi.org/10.1016/j.forsciint.2021.110691.
Zhang, L., & Wei, D. (2019). Dual DCT-DWT-SVD digital watermarking algorithm based on particle swarm optimization. Multimedia Tools and Applications, 78(19), 28003-28023. DOI: https://doi.org/10.1007/s11042-019-07902-9.
Zhang, X., Peng, F., & Long, M. (2018). Robust coverless image steganography based on DCT and LDA topic classification. IEEE Transactions on Multimedia, 20(12), 3223-3238.. DOI: 10.1109/TMM.2018.2838334.
Zhao, X., Huang, P., & Shu, X. (2022). Wavelet-Attention CNN for image classification. Multimedia Systems, 28(3), 915-924. DOI: https://doi.org/10.1007/s00530-022-00889-8.
Zheng, P., & Zhang, Y. (2020). A robust image watermarking scheme in hybrid transform domains resisting to rotation attacks. Multimedia Tools and Applications, 79(25), 18343-18365. DOI: https://doi.org/10.1007/s11042-019-08490-4.
Zhong, X., Das, A., Alrasheedi, F., & Tanvir, A. (2023). A brief, in-depth survey of deep learning-based image watermarking. Applied Sciences, 13(21), 11852. DOI: https://doi.org/10.3390/app132111852.
Zhong, X., Huang, P. C., Mastorakis, S., & Shih, F. Y. (2020). An automated and robust image watermarking scheme based on deep neural networks. IEEE Transactions on Multimedia, 23, 1951-1961. DOI: 10.1109/TMM.2020.3006415.
Authors
Copyright (c) 2026 Aqeel H. Younus, and Abdulhakeem O. Mohammed
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License [CC BY-NC-SA 4.0] that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work, with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online.