Capsule networks embedded with prior known support information for image reconstruction

作     者：Meng Wang Ping Yang Yahao Zhang 

作者机构：Department of Mathematics and PhysicsBeijing Information Science and Technology UniversityBeijing 100192China Cybersecurity Monitoring CenterState Grid Cooperation of China Information&Telecommunication BranchBeijing 100053China 

出 版 物：《High-Confidence Computing》 (高置信计算（英文）)

年 卷 期：2023年第3卷第4期

页      面：1-6页

核心收录：

学科分类：0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 

基　　金：supported by the Research Fund Project of Beijing Information Science and Technology University(2021XJJ44 and 2021XJJ69) 

主　　题：Image reconstruction Capsule networks Signal processing 

摘      要：Compressed sensing(CS)has been successfully applied to realize image *** networks have been introduced to the CS of images to exploit the prior known support information,which can improve the reconstruction *** Network(Caps Net)is the latest achievement in neural networks,and can well represent the instantiation parameters of a specific type of entity or part of an *** study aims to propose a Caps Net with a novel dynamic routing to embed the information within the CS *** output of the network represents the probability that the index of the nonzero entry exists on the support of the signal of *** lead the dynamic routing to the most likely index,a group of prediction vectors is designed determined by the ***,the results of experiments on imaging signals are taken for a comparation of the performances among different *** is concluded that the proposed capsule network(Caps Net)creates higher reconstruction quality at nearly the same time with traditional Caps Net.