CNN approach for medical image authentication

B Madhu; Ganga Holi

doi:10.17485/IJST/v14i4.1963

Article

CNN approach for medical image authentication

VIEWS 2054
PDF 1298

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v14i4.1963

Year: 2021, Volume: 14, Issue: 4, Pages: 351-360

Original Article

CNN approach for medical image authentication

B Madhu¹, Ganga Holi^2*

¹Assistant Professor, Department of Computer science and Engineering, Dr. Ambedkar Institute of Technology, Outer ring road, Bengaluru, India. Tel.: +919945187060
²Professor and Head , Department of Information Science and Engineering, AMC Engineering College, Bengaluru, 560083

*Corresponding Author
Email: [email protected]

Received Date:29 October 2020, Accepted Date:13 January 2021, Published Date:02 February 2021

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objectives: To propose a Non-blind watermarking based on a Convolutional Neural Network (CNN). Methodology: An iterative learning model is proposed to ensure robustness and imperceptibility of watermarking process. In the first step, Stationary Wavelet Transformation (SWT) and Singular Value Decomposition (SVD) are used for the initial transformation and for embedding. The neural network is used to determine the relationship between host and watermarked image to extract the watermark. Findings: We have implemented our algorithm using Magnetic Resonant Imaging (MRI) and Computerized Tomography (CT), Mammogram and Retinal Images with different attacks and proved to have good robustness with Normalized Correlation coefficient (NC) value of 0.99 and invisibility feature with Peak Signal to Noise Ratio (PSNR) of 43.77 DB. We have compared our method with that of others and it proves to be good in terms of PSNR and NC values. Novelty/Application: This study provides a novel method to train CNN with both watermarked , attacked images and to classify them.

Keywords: Medical image authentication; stationary wavelet transform; convolutional neural networks; singular value decomposition

References

Hassan B, Ahmed R, Li B, Hassan O. An Imperceptible Medical Image Watermarking Framework for Automated Diagnosis of Retinal Pathologies in an eHealth Arrangement. IEEE Access. 2019;7:69758–69775. Available from: https://dx.doi.org/10.1109/access.2019.2919381
Boroumand M, Chen M, Fridrich J. Deep Residual Network for Steganalysis of Digital Images. IEEE Transactions on Information Forensics and Security. 2019;14(5):1181–1193. Available from: https://dx.doi.org/10.1109/tifs.2018.2871749
Assem M. A “A time-efficient optimization for robust image watermarking using Machine Learning. International Journal Expert Systems with Applications. 2018;p. 197–210. Available from: https://doi.org/10.1016/j.eswa.2018.02.002
Kumar P, Sharma AK. A Robust Image Watermarking Technique using feature Optimization & Cascaded Neural Network. International Journal of Computer Science and Information Security. 2019;17(8):36–45. Available from: https://sites.google.com/site/ijcsis/
Islam MS, Ullah MA, Dhar JP. An imperceptible & robust digital image watermarking scheme based on DWT, entropy and neural network. Karbala International Journal of Modern Science. 2019;5(1):36–44. Available from: https://dx.doi.org/10.33640/2405-609x.1068
Ramamurthy N. The Robust Digital Image Watermarking scheme with Back Propagation Neural Network in DWT Domain. In: International Conference on Modeling, Optimization and Computing Procedia Engineering (ICMOC-2012) proceedings in Science Direct. p. 3769–3778.
Yamashita R, Nishio M, Do RKG, Togashi K. Convolutional neural networks: an overview and application in radiology. Insights into Imaging. 2018;9(4):611–629. Available from: https://dx.doi.org/10.1007/s13244-018-0639-9
Darvish HB, Chen F. Deep-Signs: An End-to-End Watermarking Framework for Ownership Protection of Deep Neural Networks. In: ASPLOS Proceedings ASPLOS '19. (pp. 485-497).
Zhen W, Mo S, Jin X, Qu Y, Dengx F, Shuaix J, et al. Robust and High Capacity Watermarking for Image-Based on DWT-SVD and CNN. In: IEEE Conference Industrial Electronics and Applications (ICIEA). p. 1233–1237.
Chopra D, Gupta P, BCGS, Gupta A. Lsb Based Digital Image Watermarking For Gray Scale Image. IOSR Journal of Computer Engineering. 2012;6(1):36–41. Available from: https://dx.doi.org/10.9790/0661-0613641
Zubov IG, Lysenko NV, Labkov GM, Labkov. Detection of the Information hidden in the image by Convolutional Neural Networks. In: IEEE Conference. p. 393–394.
Convolutional Neural Network. Available from: https://en.wikipedia.org/wiki/Convolutional_neural_networkaccessedon11th (accessed 2020-06-11)
AtoanyFierro-Radilla, Nakano-Miyatake M, Cedillo-Hernandez M, Cleofas-Sanchez L, Perez-Meana H. A Robust Image Zero-watermarking using Convolutional Neural Networks. International Workshop on Biometrics and Forensics (IWBF). ;p. 1–6. Available from: https://doi.org/10.1109/IWBF.2019.8739245
Anand A, Singh AK, Zhihan V, Bhatnagar G. Compression-then-Encryption based Secure Watermarking Technique for Smart Healthcare System. IEEE Computer Society. Available from: https://doi.org/10.1109/mmul.2020.2993269
Holi G, Jain DK. Convolutional Neural Network Approach for Extraction and Recognition of Digits from Bank Cheque Images”, Springer Nature Singapore. In: Lecture Notes in Electrical Engineering. (Vol. 545, pp. 331-341).
Available from: http://www.isi.uu.nl/Research/Databases/DRIVE/ (accessed 2020-06-20)
Mammoimage database. Available from: https://www.mammoimage.org/databases/ (accessed 2020-06-10)
Jane O, Elbaşi E, İlk HG. Hybrid Non-Blind Watermarking Based on DWT and SVD. (Vol. 12, pp. 750-761) Universidad Nacional Autonoma de Mexico. 2014.
Vathsala MK, Holi G. RNN based machine translation and transliteration for Twitter data. International Journal of Speech Technology. 2020;23(3):499–504. Available from: https://dx.doi.org/10.1007/s10772-020-09724-9
Perez H, Tah JHM. Improving the Accuracy of Convolutional Neural Networks by Identifying and Removing Outlier Images in Datasets Using t-SNE. Mathematics. 2020;8. Available from: https://dx.doi.org/10.3390/math8050662

Copyright

© 2021 Madhu & Holi.This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)