A Multi-Watermarking Algorithm for Medical Images Using Inception V3燼nd燚CT

Abstract

Medical images are a critical component of the diagnostic process for clinicians. Although the quality of medical photographs is essential to the accuracy of a physician's diagnosis, they must be encrypted due to the characteristics of digital storage and information leakage associated with medical images. Traditional watermark embedding algorithm embeds the watermark information into the medical image, which reduces the quality of the medical image and affects the physicians' judgment of patient diagnosis. In addition, watermarks in this method have weak robustness under high-intensity geometric attacks when the medical image is attacked and the watermarks are destroyed. This paper proposes a novel watermarking algorithm using the convolutional neural networks (CNN) Inception V3 and the discrete cosine transform (DCT) to address above mentioned problems. First, the medical image is input into the Inception V3 network, which has been structured by adjusting parameters, such as the size of the convolution kernels and the typical architecture of the convolution modules. Second, the coefficients extracted from the fully connected layer of the network are transformed by DCT to obtain the feature vector of the medical image. At last, the watermarks are encrypted using the logistic map system and hash function, and the keys are stored by a third party. The encrypted watermarks and the original image features are performed logical operations to realize the embedding of zero-watermark. In the experimental section, multiple watermarking schemes using three different types of watermarks were implemented to verify the effectiveness of the three proposed algorithms. Our NC values for all the images are more than 90% accurate which shows the robustness of the algorithm. Extensive experimental results demonstrate the robustness under both conventional and high-intensity geometric attacks of the proposed algorithm.

Hybrid watermarking and encryption techniques for securing three-dimensional information

“…The table reveals that our algorithm's NC value exceeds that of [14,20] in rotation attacks. In terms of cropping, our algorithm surpasses all listed algorithms, and in scaling attacks, its NC values outperform those of [15,16,20]. During compression attacks with a 25% compression ratio our algorithm outperforms [14][15][16]20].…”

“…The comparison results are displayed in table 2. Against Gaussian noise attacks, our algorithm exhibits superior resistance compared to the algorithms [14][15][16]20]. Additionally, our algorithm outperforms others in median filtering attacks, achieving an NC value of 0.9 or higher.…”

“…Our approach's robustness was benchmarked against algorithms [14][15][16]20], showing superior resilience to traditional image processing, geometric and conventional attacks. The comparison results are displayed in table 2.…”

“…For instance, in 2021, Yi et al [14] proposed a robust zerowatermarking algorithm based on Polar Harmonic transforms (PHTs) and discrete cosine transform (DCT) for medical images in the encrypted domain, using a tent chaotic sequence to encrypt the image and enhance the security of the carrier image information. In 2022, Fan et al [15] proposed a novel watermarking algorithm for medical images. The method, combined with the convolutional neural networks (CNN) Inception V3 and DCT for preprocessing original medical images and extracting features, exhibits strong robustness.…”

Robust Multi-Watermarking Algorithm for Medical Images Based on GoogLeNet and Henon Map

“…In the experimental process, we selected the same size of brain map and text "HN" watermark information for testing to maintain uniformity. Then, we compared with the existing algorithms KAZE-DCT [30], Zernike-DCT [31], Inception V3-DCT [32], and DWT-DCT. As can be seen, from both Table 6 and Fig.…”