Article: Robust zero-watermarking technique based on DO-ResNet and Adaptive Pelican Optimisation Journal: International Journal of Signal and Imaging Systems Engineering (IJSISE) 2024 Vol.13 No.3 pp.109 - 132 Abstract: This research presents a revolutionary deep learning-based zero watermarking technology that appears to increase image security. Zero-watermarking was utilised to secure the copyright data of highly invisible images. The pretrained DO-ResNet model was developed to extract high-dimensional deep features from images. The deep features are selected using low-frequency coefficients of the discrete Fourier transform (DFT). Furthermore, employing an adaptive Pelican optimisation (APO) algorithm, the loss of result in the optimal area can be reduced. The experimental results demonstrate that the approach is robust, secure, invisible and it can obtain watermark information reliably. The proposed method handles geometric and common attacks more efficiently by automatically extracting high-dimensional, complex information from images. The obtained simulation results demonstrate that the USC-SIPI dataset, the proposed method performs better in terms of accuracy (99.32%), PSNR (51.62), and SSIM (97.35). For the MS-COCO dataset, the proposed method attains an accuracy (98.45%), PSNR (37.58%), and SSIM (93.25%). Inderscience Publishers - linking academia, business and industry through research

Title: Robust zero-watermarking technique based on DO-ResNet and Adaptive Pelican Optimisation

Authors: Sambhaji Marutirao Shedole; V. Santhi

Addresses: School of Computer Science and Engineering, Vellore Institute of Technology, Katpadi, Vellore, Tamil Nadu 632014, India ' School of Computer Science and Engineering, Vellore Institute of Technology, Katpadi, Vellore, Tamil Nadu 632014, India

Abstract: This research presents a revolutionary deep learning-based zero watermarking technology that appears to increase image security. Zero-watermarking was utilised to secure the copyright data of highly invisible images. The pretrained DO-ResNet model was developed to extract high-dimensional deep features from images. The deep features are selected using low-frequency coefficients of the discrete Fourier transform (DFT). Furthermore, employing an adaptive Pelican optimisation (APO) algorithm, the loss of result in the optimal area can be reduced. The experimental results demonstrate that the approach is robust, secure, invisible and it can obtain watermark information reliably. The proposed method handles geometric and common attacks more efficiently by automatically extracting high-dimensional, complex information from images. The obtained simulation results demonstrate that the USC-SIPI dataset, the proposed method performs better in terms of accuracy (99.32%), PSNR (51.62), and SSIM (97.35). For the MS-COCO dataset, the proposed method attains an accuracy (98.45%), PSNR (37.58%), and SSIM (93.25%).

Keywords: MPHF; mean perceptual hash function; watermarking extraction algorithm; watermarking embedding algorithm; HCNN; Hermite chaotic neural network; APO; adaptive Pelican optimisation; common attacks; and geometric attacks.

DOI: 10.1504/IJSISE.2024.143819

International Journal of Signal and Imaging Systems Engineering, 2024 Vol.13 No.3, pp.109 - 132

Received: 23 Dec 2023
Accepted: 21 Aug 2024
Published online: 08 Jan 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Robust zero-watermarking technique based on DO-ResNet and Adaptive Pelican Optimisation

Keep up-to-date