An Optimized Watermarking Technique for Medical Images using Dimension Reduction
Zeynep Çetinkaya, Fahrettin Horasan · 2025
Advancements in technology have enabled the widespread use of digital systems for the creation, processing, distribution, and storage of medical images. Numerous advantages are achieved with the effective use of technology, but security risks such as manipulation of medical data, unauthorized access, deletion or copying pose significant challenges in these processes. In this context, ensuring the originality and security of medical images has become a critical necessity. Recent advancements have led to increased research on applying watermarking techniques in medical imaging to address this issue. In this study, a novel medical image watermarking algorithm incorporating dimension reduction, Discrete Wavelet Transform (DWT) and Singular Value Decomposition (SVD), was developed. To increase the efficiency of the proposed scheme Particle Swarm Optimization (PSO) algorithm, a well-established optimization algorithms, was utilized. To determine the performance of the watermarking scheme, PSNR and SSIM metrics were computed and NC values were examined under various attack scenarios. The results indicate that the best PSNR value was found to be 53.8253 dB. NC and SSIM values produced results very close to $\mathbf{1}$. Based on these findings, it is concluded that the proposed watermarking scheme provides high levels of confidentiality, durability and imperceptibility as intended.