MFFWmark: multifocus fusion-based image watermarking for telemedicine applications with BRISK feature authentication

The increasing use of the internet makes it much harder to safeguard images using copyright. By storing, transmitting, and processing data, watermarking systems can prevent interference and safeguard the copyright of digital multimedia content. Important attributes of image watermarking include imperceptibility, robustness, and reliability with sufficient embedding capacity. For medical applications, the multimedia data volume has vividly expanded. When two medical images are fused, the combined data of both images are transformed at the same time and the data volume is reduced. In this chapter, a two-level decomposition- and integer wavelet transform (IWT)-based image watermarking system is presented. The IWT-processed cover image is decomposed in the suggested scheme using the Schur decomposition and singular value decomposition (SVD) techniques. In this work, two watermark images, (1) a brain MRI and (2) a brain CT scan, are fused using the multifocus image fusion technique in the discrete cosine transform (DCT) domain and embedded into the Digital Imaging and Communications in Medicine (DICOM) ultrasound image of a liver using IWT and multiple decompositions. The watermark image is fused using two fusion techniques with and without consistency verification and the performance of the proposed scheme is compared for both fused watermarks. Several attacks, including filtering, image compression, and checkmark attacks, are applied to estimate the performance of the suggested system. The suggested approach yields a peak signal-to-noise ratio (PSNR) value of about 37 dB (without attack) and successfully extracts the watermark because the resulting normalized correlation coefficient (NCC) is 1.0000. The authentication of watermarked images is done using binary robust invariant scalable key point (BRISK) features.