Deep learning‐based robust medical image watermarking exploiting DCT and Harris hawks optimization

Chacko, Anusha; Chacko, Shanty

doi:10.1002/int.22742

Cited by 16 publications

(6 citation statements)

References 37 publications

(80 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Robustness is amplified by the incorporation of perturbations during the training phase, underscoring an enhanced resilience to various forms of distortions and manipulations. Chack et al [63] introduced a hybrid methodology that intertwines traditional watermarking, CNN, and evolutionary optimization. This multifaceted approach embeds an Arnold-transformed watermark into the DCT domain, employs Harris Hawks optimization to fine-tune the embedding strength, and relies on a CNN to uncover the embedded watermark.…”

Section: Hybrid Methodsmentioning

confidence: 99%

A Brief, In-Depth Survey of Deep Learning-Based Image Watermarking

Zhong,

Das,

Alrasheedi

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

This paper presents a comprehensive survey of deep learning-based image watermarking; this technique entails the invisible embedding and extraction of watermarks within a cover image, aiming for a seamless combination of robustness and adaptability. We navigate the complex landscape of this interdisciplinary domain, linking historical foundations, current innovations, and prospective developments. Unlike existing literature, our study concentrates exclusively on image watermarking with deep learning, delivering an in-depth, yet brief analysis enriched by three fundamental contributions. First, we introduce a refined categorization, segmenting the field into embedder–extractor, deep networks for feature transformation, and hybrid methods. This taxonomy, inspired by the varied roles of deep learning across studies, is designed to infuse clarity, offering readers technical insights and directional guidance. Second, our exploration dives into representative methodologies, encapsulating the diverse research directions and inherent challenges within each category to provide a consolidated perspective. Lastly, we venture beyond established boundaries, outlining emerging frontiers and providing detailed insights into prospective research avenues.

show abstract

Section: Hybrid Methodsmentioning

confidence: 99%

A Brief, In-Depth Survey of Deep Learning-Based Image Watermarking

Zhong,

Das,

Alrasheedi

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…There are numerous weak signals that may be concentrated in a single output with a high signal-to-noise ratio because of the watermark verification process' knowledge of the watermark's position and content. It is, nevertheless, necessary to introduce noise of large amplitude to every frequency bin in order to remove a watermark [6].…”

Section: Problemmentioning

confidence: 99%

Secured Mechanism Towards Integrity of Digital Images Using DWT, DCT, LSB and Watermarking Integrations

Hassan

Allawi

2023

IHJPAS

View full text Add to dashboard Cite

"Watermarking" is one method in which digital information is buried in a carrier signal; the hidden information should be related to the carrier signal. There are many different types of digital watermarking, including traditional watermarking that uses visible media (such as snaps, images, or video), and a signal may be carrying many watermarks. Any signal that can tolerate noise, such as audio, video, or picture data, can have a digital watermark implanted in it. A digital watermark must be able to withstand changes that can be made to the carrier signal in order to protect copyright information in media files. The goal of digital watermarking is to ensure the integrity of data, whereas steganography focuses on making information undetectable to humans. Watermarking doesn't alter the original digital image, unlike public-key encryption, but rather creates a new one with embedded secured aspects for integrity. There are no residual effects of encryption on decrypted documents. This work focuses on strong digital image watermarking algorithms for copyright protection purposes. Watermarks of various sorts and uses were discussed, as well as a review of current watermarking techniques and assaults. The project shows how to watermark an image in the frequency domain using DCT and DWT, as well as in the spatial domain using the LSB approach. When it comes to noise and compression, frequency-domain approaches are far more resilient than LSB. All of these scenarios necessitate the use of the original picture to remove the watermark. Out of the three, the DWT approach has provided the best results. We can improve the resilience of our watermark while having little to no extra influence on image quality by embedding watermarks in these places.

show abstract

“…Fan et al [17] proposed a robust watermarking scheme for DWI images in medical images by combining global and local features for image reconstruction and embedding watermark redundancy into the features of multi-scale reconstruction. Chacko et al [18] proposed a combination of a discrete cosine transform and a deep learning convolutional neural network. The DCT-transformed cover image and the IF coefficients of the watermark were used as inputs to a DLCNN for watermark embedding.…”

Section: Robust Watermarkmentioning

confidence: 99%

Two-Stage Robust Lossless DWI Watermarking Based on Transformer Networks in the Wavelet Domain

Liu

Zheng

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

For copyright protection of diffusion-weighted imaging (DWI) images, traditional robust watermarking techniques result in irreversible distortions, while reversible watermarking methods exhibit poor robustness. We propose a two-stage lossless watermarking algorithm based on a Transformer network to solve this problem. The first stage of the algorithm is to train the robust watermarking network, embed the watermark into the cover image in the wavelet domain, and design the frequency information enhancement module to improve the reconstruction quality. In the second stage, based on the pre-trained robust watermarking network, the difference image between the watermarked image and the cover image is reversibly embedded into the watermarked image as the compensation information to losslessly recover the cover image. The difference image is compressed using DCT and Huffman coding to reduce the compensation information. Finally, the watermark extraction network is trained on the second embedding result to avoid weakening the robustness of the first stage caused by the reversible embedding. The experimental results demonstrate that the PSNR of the watermarked image reaches 60.18 dB. Under various types of image attacks, the watermark extraction BER is below 0.003, indicating excellent robustness. The cover image can be recovered losslessly under no attack.

show abstract

Deep learning‐based robust medical image watermarking exploiting DCT and Harris hawks optimization

Abstract: Image watermarking is an effective way to secure the ownership of digital photographs. This paper proposes a new methodology for integrating a watermark on the basis of various integrative strengths. The image is separated as 8 × 8 pixels blocks that do not overlap. The

Cited by 16 publications

References 37 publications

A Brief, In-Depth Survey of Deep Learning-Based Image Watermarking

A Brief, In-Depth Survey of Deep Learning-Based Image Watermarking

Secured Mechanism Towards Integrity of Digital Images Using DWT, DCT, LSB and Watermarking Integrations

Two-Stage Robust Lossless DWI Watermarking Based on Transformer Networks in the Wavelet Domain

Contact Info

Product

Resources

About