The transmission of medical images via medical agencies raises security concerns, necessitating increased security measures to ensure integrity and security. However, many watermarking algorithms overlook equipoise; the relation between robustness, invisibility, and payload capacity results in a less satisfactory performance. To bridge this gap, we propose a new blind watermarking method for securing medical images based on a convolutional neural network in a fusion domain. First, we transmute the host color image using a phase-only transform (PHOT) to detect the surface pattern. We feed the detected surface pattern into a pre-trained VGG19 model to impeccably extract the stable feature vector. We encrypt the extracted image features using a hybrid Chirikov map to enhance their robustness and reliability. The synergy between the pre-trained VGG19 model and PHOT in an integrated domain effectively captures additional native and localized image features. A hybrid Fibonacci Q-matrix method scrambles the binary watermark to enhance security. Integrating double encryption into the proposed method markedly enhances its resistance against diverse countermeasures. Experimental outcomes indicate that the proposed scheme performs efficiently in robustness and invisibility. The obtained PSNR value was up to 60.15 dB, which is optimal for human perception. The embedded watermark can be retrieved without any warping. The retrieved watermark seems to be authentic, exhibiting ideal BER and NC values. In almost all attack circumstances, the BER values approached zero while the NC values got closer. The proposed method demonstrates notable enhancements in robustness and invisibility compared to prior methods.

This paper proposes a new blind, color image watermarking method using fast Walsh–Hadamard transformation (FWHT) and multi-channel fractional Legendre–Fourier moments (MFrLFMs). The input host color image is first split into 4 × 4 non-interfering blocks, and the MFrLFMs are computed for each block, where proper MFrLFMs coefficients are selected and FWHT is applied on the selected coefficients. The scrambled binary watermark has been inserted in the quantized selected MFrLFMs coefficients. The proposed method is a blind extraction, as the original host image is not required to extract the watermark. The proposed method is evaluated over many visual imperceptibility terms such as peak signal-to-noise ratio (PSNR), normalized correlation (NC), and bit error rate. The robustness of the proposed method is tested over several geometrical attacks such as scaling, rotation, cropping, and translation with different parameter values. The most widely recognized image processing attacks are also considered, e.g., compressing and adding noise attacks. A set of combination attacks are also tested to analyze the robustness of the proposed scheme versus several attacks. The proposed model’s experimental and numerical results for invisibility and robustness were superior to the results of similar watermarking methods.

This paper offers a new robust-blind watermarking scheme for medical image protection. In the digital era, protecting medical images is essential to maintain the confidentiality of patients and data reliability. Robust blind watermarking has surfaced as a practical option for secure image authentication and copyright protection. A new plan uses the multidimensional fast Fourier transform (MD-FFT) and combines LZW compression with linear feedback shift register (LFSR) encryption. Nevertheless, current watermarking methodologies frequently encounter difficulties balancing endurance, invisibility, and payload capacity. Numerous methodologies inadequately offer robust protection against diverse threats while ensuring imperceptibility and effective data management. The motivation behind this successful integration is to reinforce invisibility and sturdiness. The host image is initially divided into four equal portions for rapid processing, followed by encryption using the LFSR method to increase robustness. The Multi-FFT is applied to the encrypted parts to enhance their visual invisibility. The watermark is first encoded using LZW compression, then scrambled with Arnold encryption before being embedded in the modified MD-FFT magnitudes, strengthening the protection level. The watermark is fully and blindly extracted without referencing the host image. Compared to similar methods, the proposed scheme maintains a fundamental tradeoff between robustness and visual imperceptibility against many commonly encountered attacks. The extracted watermark remains original with minimal observable distortion. Empirical findings confirm that the proposed algorithm outperforms existing watermarking methods in terms of invisibility and robustness while maintaining an acceptable payload capacity.