For the medical industry, there are problems such as poor sharing of medical data, tampering, and leakage of private data. In view of these problems, a blockchain-based electronic medical record access control research scheme based on the role-based access control model is proposed in this article. First, the appropriate access control strategy is adopted to solve the leakage problem of the user’s medical privacy information during the access process. Then, the information entropy technology is used to quantify the medical data, so that the medical data can be effectively and maximally utilized. Using the distributed general ledger characteristics of blockchain and its inherent security attributes, data islands can be eliminated, data sharing among medical systems can be promoted, access records can be prevented from being tampered with, and medical research and precise medical treatment can be better supported. Through this research, not only can user’s medical privacy information protection be realized during the service process but also patients can manage their own medical data autonomously, which is beneficial to privacy protection under the medical data sharing.

Deep learning, such as convolutional neural networks, has been achieved great success in image processing, computer vision task, and image compression, and has achieved better performance. This paper designs a multiple description coding frameworks based on symmetric convolutional auto-encoder, which can achieve high-quality image reconstruction. First, the image is input into the convolutional auto-encoder, and the extracted features are obtained. Then, the extracted features are encoded by the multiple description coding and split into two descriptions for transmission to the decoder. We can get the side information by the side decoder and the central information by the central decoder. Finally, the side information and the central information are deconvolved by convolutional auto-encoder. The experimental results validate that the proposed scheme outperforms the state-of-the-art methods.

Region of Interest (ROI)-based image compression optimizes bit allocation by prioritizing ROI for higher-quality reconstruction. However, as the users (including human clients and downstream machine tasks) become more diverse, ROI-based image compression needs to be customizable to support various preferences. For example, different users may define distinct ROI or require different quality trade-offs between ROI and non-ROI. Existing ROI-based image compression schemes predefine the ROI, making it unchangeable, and lack effective mechanisms to balance reconstruction quality between ROI and non-ROI. This work proposes a paradigm for customizable ROI-based deep image compression. First, we develop a Text-controlled Mask Acquisition (TMA) module, which allows users to easily customize their ROI for compression by just inputting the corresponding semantic text. It makes the encoder controlled by text. Second, we design a Customizable Value Assign (CVA) mechanism, which masks the non-ROI with a changeable extent decided by users instead of a constant one to manage the reconstruction quality trade-off between ROI and non-ROI. Finally, we present a Latent Mask Attention (LMA) module, where the latent spatial prior of the mask and the latent Rate-Distortion Optimization (RDO) prior of the image are extracted and fused in the latent space, and further used to optimize the latent representation of the source image. Experimental results demonstrate that our proposed customizable ROI-based deep image compression paradigm effectively addresses the needs of customization for ROI definition and mask acquisition as well as the reconstruction quality trade-off management between the ROI and non-ROI. Additionally, even by using the uniform mask as input, our method still outperforms the anchor methods in image reconstruction and machine vision tasks (such as object detection and instance segmentation). Our source code will be available at: https://github.com/hccavgcyv/Customizable-ROI-Based-Deep-Image-Compression.

Recently, region-based 3-D video coding has been proposed. However, existing view synthesis distortion estimation (VSDE) methods are performed at the frame level. To guide the rate-distortion optimization process of region-based 3-D video coding schemes, this paper proposes the first pixel-level VSDE (PL-VSDE) method. We first give the definition of the pixel-level view synthesis distortion. To estimate it, a backward prediction method is then developed, which starts from the pixels of interest (POIs) in the virtual view and finds their corresponding pixels in the reference view via a coarse-to-fine approach, denoted as coarse-to-fine backward prediction (CFBP) method. Additionally, the CFBP fully considers the details of 3-D warping, the rounding operation and the warping competition in view synthesis, leading to improved accuracy of the prediction. Besides, a table-lookup method and a warping property are introduced to speed up the CFBP. After integrating the CFBP into the PL-VSDE, we can estimate the view synthesis distortion at the pixel level. Our method is carried out pixel-by-pixel independently, which is friendly for parallel processing. Experimental results demonstrate that our proposed method has significant advantages in both accuracy and efficiency compared with state-of-the-art frame-level VSDE methods.

In this paper, we present a new multiple description coding scheme, which is based on a sparse dictionary training method called K singular value decomposition (KSVD). In the proposed scheme, each description encodes one source subset with a small quantization stepsize, and other subsets are predictively coded with a large quantization stepsize. The source processed by the KSVD becomes sparse, which can improve the coding efficiency. The proposed scheme is then applied to lapped transform-based multiple description image coding. Finally, image coding results show that the proposed scheme achieves better performance than the current state-of-the-art multiple description coding methods.