基于稀疏和低秩约束的压缩感知图像重建算法  

A Compressive Sensing Image Reconstruction Algorithm Based on Low-rank and Total Variation Regularization

作　　者：朱俊[1] 陈长伟[2] 

机构地区：[1]金陵科技学院计算机工程学院,江苏南京211169 [2]南京晓庄学院信息工程学院,江苏南京211194

出　　处：《金陵科技学院学报》2015年第4期23-26,共4页Journal of Jinling Institute of Technology

基　　金：金陵科技学院博士启动基金(jit-b-201508)

摘　　要：压缩感知(Compressive sensing,CS)图像重建算法是CS图像获取问题的一个研究重点。针对基于低秩先验的重建算法不能有效重建图像的局部几何特征,为了进一步提高图像的重建质量,在低秩先验的基础上,引入稀疏约束作为图像额外的先验知识,建立了基于低秩和总变差约束的CS图像重建模型,并给出了相应的优化算法。试验结果表明,与传统的稀疏性先验重建算法和最好的NLR(Compressive sensing via nonlocal low-rank regularization)算法相比,该试验所提的算法能够获得更好的图像重构效果。Compressive sensing（CS）image reconstruction algorithm is a key point in the CS image acquisition.The low-rank reconstruction algorithms cannot effectively reconstruct various image structures.In order to improve the reconstruction precision with the same number of measurements,the sparsity regularization is introduced as the additional prior information of image,and a reconstruction model based on low-rank property and Total variation（TV）CS image has been proposed.We also propose the relative numerical algorithm in the paper.Compared with the traditional sparsity regularized algorithms and Compressive sensing via nonlocal lowrank regularization（NLR）method which shows the state-of-the-art performance,the proposed algorithm can achieve better image reconstruction results.

关 键 词：压缩感知 图像重建 总变差 低秩属性 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]