This paper introduces a hybrid image verification and authentication technique, integrating reversible-watermarking with zero-watermarking to improve the security of medical images. In zero-watermarking, a convolutional neural network extracts specific image features and merges them with a patient's image to create a master share. To increase the robustness, the QR code is fused with the master share. The QR code is embedded into the image using a reversible watermarking technique into Regions of Non-Interest detected by the K-means algorithm, ensuring the optimal region for the QR code embedding into the middle-frequency coefficients of the Discrete Fourier Transform. The experimental results validate the robustness of the proposed scheme despite applying different ge-ometric transformations and image processing distortions to the watermarked image. The results demonstrate that our method preserves image quality and recovers the watermark efficiently. The obtention of a low bit error rate and high normalized cross-correlation values evidences the efficiency.
Cellular internet of things (CIoT) technologies are recognized as the best match for the industry sector as potential enablers of secured, reliable, and long-range communication. Namely, the narrowband iot (NB-IoT) and LTE Cat-M technologies fall into already proven representatives defined by the 3GPP organization and integrated into the licensed frequency spectrum. Being able to meet the increasing requirements of the customers and the regulation bodies, i.e., 5G ITU-R M.2410, the industry needs to follow the accelerated trends in the CIoT and test new communication modules or even technologies (5G RedCap) to improve the communication parameters of their products. In this paper, we report on the key aspects of the hardware design of the universal development platform for massive machine-type communication (mMTC). The given choices, i.e., platform-related decisions and hardware design, are supported by longterm cooperation with the leading telecommunication operators and distributors, confirmed by successful deployment and real-life measurement campaigns.
Real-time services are everywhere in our lives, including activities such as voice calls, live streaming, and cloud gaming. These services face significant challenges, such as scalability, availability, and maintenance burden due to high demand. To address these challenges, we propose a new architecture that leverages the QUIC protocol to provide multi-cloud/multi-region media services that can be scaled beyond the limits of the current real-time services. Our architecture eliminates the need for communication between the control plane and the data plane, resulting in even higher scalability. We compare our architecture based on load and delay distribution to Jitsi, a commercially available distributed video-conferencing service, within a Kubernetes multi-region environment. Our findings show that our architecture can achieve comparable or superior performance compared to existing solutions, while giving better scalability. This study demonstrates the potential to improve real-time services by strategically locating media servers closer to end users.
Multimodal biometric systems are becoming more and more popular because they allow to improve the overall performance of unimodal ones. Ultrasound systems have the peculiarity of collecting 3D image that contains information on different biometric characteristics. In the present work, a technique for collecting volumetric images of the palm based on an advanced ultrasound scanner (ULA OP 256) and compound plane waves is proposed and experimentally evaluated. Good quality images were achieved by transmitting 17 steered plane waves in the range +/- 3.15 degrees. Image field depth was sufficiently high to extract both palmprint and vein patterns. Recognition capabilities are evaluated through palmprint verification and identification experiments on a homemade database composed of 216 samples from 47 users, obtaining very good results (EER=0.26% and identification rate=100%). It has also been experimentally verified that the proposed system allows to sensibly speed up the acquisition process without image quality loss. Further potentialities of the proposed approach are finally discussed.
Aortic valve calcium scoring is extensively utilized for diagnosing, treating, monitoring, and assessing the risk of aortic stenosis and coronary artery disease. The gold standard method for determining aortic valve calcium score is computed tomography (CT). However, CT is expensive and exposes patients to radiation. Alternatively, echocardiography, which is a cheaper and radiation-free method, may not provide an objective result due to inter- and intra-observer variability among cardiologists. Therefore, automated measurement of aortic valve calcium score is essential. In this paper, a fully convolutional neural network approach is proposed for the segmentation of aortic valve calcified regions from echocardiography images, as the first step in predicting aortic valve calcium score. This aims to achieve a more objective, faster, easier, less costly, and radiation-free automatic calculation of aortic valve calcium score. The proposed method achieves a precision of 86.3%, recall of 80.27%, a dice coefficient of 76.27%, and a Jaccard index of 61.9% on the new dataset including 118 echocardiography images across 82 individual patients. These results show the feasibility and potential efficacy of fully automating aortic valve calcium scoring from echocardiography images.
