International Research Journal of Education and Technology

Transferring and Protecting a patient data in crucial in telemedicine application. In order to protect the security and integrity of private medical information, this research investigates a reliable digital picture watermarking method designed specifically for medical photos. The Discrete Wavelet Transform (DWT) is used in the watermark embedding procedure to efficiently insert the watermark by breaking down the medical image into several frequency sub- bands. An U-Net architecture is initially used for image segmentation, which helps to isolate important regions of interest (ROIs) in the medical pictures, improving watermark embedding while lowering the possibility of data loss or distortion in crucial areas. The watermark is subjected to scrambling techniques to increase security and robustness, making it more difficult for unauthorized individuals to extract it. The Inverse Discrete Wavelet Transform (IDWT) is used to recover the watermarked image as part of the watermark extraction procedure. Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM), two well- known metrics that evaluate the quality of the watermarked and extracted pictures, are used to evaluate performance. The suggested approach is a potential solution for safe medical image sharing and authentication since experimental findings show how effective it is in terms of watermark imperceptibility, resilience to attacks, and maintenance of medical image

quality.

Key Words: Watermarking, DWT, performance evaluation, U-NET architecture, data loss, telemedicine, authentication