基于压缩感知和稀疏表示的数据重建与去噪算法研究  

RESEARCH ON DATA RECONSTRUCTION AND DENOISING ALGORITHM BASED ON COMPRESSED SENSING AND SPARSE REPRESENTATION

作　　者：宋娜 

机构地区：[1]郑州工业应用技术学院信息工程学院,河南郑州451100

出　　处：《南阳理工学院学报》2017年第4期32-36,共5页Journal of Nanyang Institute of Technology

基　　金：河南省科技攻关计划项目(NO.0721002210032)

摘　　要：传统的数据重建算法受奈奎斯特采样定理限制,采样率要求较高不能灵活等适应实际环境。本文基于压缩感知和稀疏表示理论,提出一种采样点少且流形结构简单的图像重建算法,以少量的采样数据实现从低分辨率观测中恢复高分辨率图像。算法首先通过原始数据特征设计出稀疏表示矩阵;其次,根据表示数据和观测数据的不相关性找出与稀疏表示矩阵对应的最优感知矩阵;最后,通过稀疏求解实现数据的重建与去噪。实验表明,该算法在同等条件下能够避免大量冗余数据的计算,提高数据重建的稳定性和有效性。The traditional data reconstruction algorithm is limited by the Nyquist sampling theorem,and the higher sampling rate is not flexible enough to adapt to the actual environment. Based on the theory of compression sensing and sparse representation,a simple image reconstruction algorithm with low sampling points and simple manifold structure is proposed,recover high-resolution images from low-resolution observations with a small amount of sampled data. The algorithm first designs the sparse representation matrix through the original data feature; secondly,the optimal perceptual matrix corresponding to the sparse representation matrix is found according to the irrelevance of the data and the observed data; finally,the data is reconstructed and denoised by sparse solution. Experiments show that the algorithm can avoid the calculation of large amount of redundant data under the same conditions,and improve the stability and validity of data reconstruction.

关 键 词：压缩感知 稀疏表示 数据重建 去噪 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]