Deep Learning & Hybrid Model – The Future of Medical Image Watermarking?

Authors

  • Yew Lee Wong TUNKU ABDUL RAHMAN UNIVERSITY COLLEGE
  • Jia Cheng Loh
  • Chen Zhen Li
  • Chi Wee Tan

Keywords:

Invisible Watermarking, DCT, DWT, SVD, RivaGAN, Deep-Learning-Based Invisible Watermarking

Abstract

The frequent usage of medical records in electronic form has made Medical Image Watermarking (MIW) relatively significant that it used to be. MIW is very significant as to preserve the completeness and integrity of medical image. For the time being, with the trade-offs between visibility and robustness, there are no perfect algorithms for invisible watermarking. Many novel Deep-Learning-Based Approach has been proposed to solve the tradeoffs. In this study, multiple implementations of invisible watermarking techniques such as Deep-Learning-Based Approach and Non-Deep-Learning-Based-Approach are being compared. This comparative study measures the limitations and robustness on a dataset of breast ultrasound images. 18 extreme attacking methods were carried out on the encoded images, performance was then evaluated using PSNR and NCC. Encoded images were then tested against a digital transmission channel to test its robustness. To conclude, The Deep-Learning-Based-Approach of RivaGAN showed the best robustness against multiple extreme attacks. The Non-Deep-Learning-Based-Approach of DWT-DCT-SVD has the best imperceptibility. Therefore, we confirm the feasibility of Deep-Learning-Based-Approach in Medical Image Watermarking, however more work is needed to be done to achieve perfect Deep-Learning-Based-Approach in terms of imperceptibility.

Downloads

Published

24-11-2022

How to Cite

Wong, Y. L., Loh, J. C., Li, C. Z., & Tan, C. W. (2022). Deep Learning & Hybrid Model – The Future of Medical Image Watermarking?. The Journal of The Institution of Engineers, Malaysia, 82(3). Retrieved from https://iemjournal.com.my/index.php/iem/article/view/121