Enhanced brain image security using a hybrid of lifting wavelet transform and support vector machine

Thanks to technological improvements, digital picture watermarking has emerged as a useful method for preventing unlawful use and manipulation of digital photographs. Providing robustness against geometrical assault while maintaining an adequate level of security and imperceptibility is a basic challenge in digital picture watermarking. With the use of support vector machine (SVM) and lifting wavelet transform (LWT), this study offers an effective authentication approach for digital image watermarking on medical images. To distinguish between the region of interest (ROI) and the non-region of interest (NROI) in the medical image, SVM is first employed in this article. After that, LWT is used to incorporate watermark data into the medical image's NROI section (cover image). Additionally, a shared secret key has been used to increase the suggested scheme's resilience. A vast image database is used to test the method's performance in various scenarios. To determine whether the current plan was acceptable, the study examined several experimental investigations. The experimental results give a PSNR value of 67.81 dB and a structural similarity index measure value of 0.9999, Where the PSNR improvement percentage is 13.9462 dB, showing durability and imperceptibility for the proposed watermarking model.