Robust Image Watermarking in Wavelet Domain using GBT-DWT-SVD and Whale Optimization Algorithm

TL;DR

This paper presents a robust digital image watermarking method combining GBT, DWT, SVD, and Whale Optimization Algorithm to enhance ownership verification and resist image attacks.

Contribution

It introduces a novel watermarking technique that optimally embeds watermarks using whale optimization to improve robustness and image quality.

Findings

High PSNR and NC values under attack conditions

Outperforms existing watermarking methods in robustness

Effective in preserving image quality after embedding

Abstract

As digital content can be copied easily, Copyright infringement has become a concern nowadays. Providing a solution to prevent the abuse of such contents is very necessary. One of the most common methods to solve this problem is watermarking. In this method, a logo belongs to the owner of the media is embedded in the media. So, they can prove the originality or ownership of the media content. Images are one of the most important digital media. Therefore, in this study, a method for digital image watermarking is proposed. The proposed method is based on Graph-based Transform (GBT), Singular Value Decomposition (SVD), and Discrete Wavelet Transform (DWT) which uses a Whale Optimization Algorithm (WOA) to find the best value for the embedding coefficient in the images as well as optimal blocks. The image is first transformed to a transform domain using the DWT and GBT, and then the watermark logo embedded onto the singular values of the cover image. The objective function defined for this task is based on the three parameters PSNR and NC, in the presence of image attacks. The results of the proposed algorithm on some known images show a high performance of this method compared to other similar methods.