Robust Digital Image Watermarking Enhanced Through Particle Swarm Optimization

Ms. Umadevi V. Shintre , Dr. Mrs. P. P. Belagali

Keywords: Digital Watermarking, Hybrid Watermarking, DWT, DCT, SVD, Particle Swarm Optimization (PSO), Robustness, Imperceptibility, Scaling Factor.

Digital image watermarking is an essential technique for ensuring copyright protection, proving ownership, and preventing tampering of digital media. Traditional watermarking methods, whether spatial-domain or transform-domain, often struggle to strike an optimal compromise between two core requirements: robustness (resistance to attacks) and imperceptibility (visual quality of the watermarked image). This difficulty is often attributed to the use of a fixed, manually set scaling factor (phi) during embedding, which may not be appropriate for diverse images or various attack scenarios. This paper presents a robust, non-blind hybrid image watermarking technique that integrates Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT), and Singular Value Decomposition (SVD), which is then dynamically optimized using Particle Swarm Optimization (PSO). The PSO algorithm is employed to automatically identify the optimal scaling factor (phi), which maximizes a fitness function defined by balancing the Peak Signal-to-Noise Ratio (PSNR) for visual quality and the Normalized Correlation (NC) for watermark recovery accuracy. The proposed methodology involves using DWT for initial host image decomposition, followed by applying DCT and SVD to specific DWT sub-bands, while SVD is also applied to the watermark to extract its vital components. The watermark is embedded by modifying the singular values, guided by the optimal phi determined by PSO. The expected results indicate that the PSO-based adaptive system achieves high PSNR and NC values, delivering stronger, more reliable performance and accurate watermark recovery.

Volume 10 Issue 12, December-2025

Pages : b31-b40