Image Reconstruction using Orthogonal Matching Pursuit (OMP) Algorithm

被引：0

作者：

Goklani, Hemant S. ^{[1
]}

Sarvaiya, Jignesh N. ^{[1
]}

Fahad, A. M. ^{[1
]}

机构：

[1] SVNIT, ECED Dept, Surat 392001, Gujarat, India

来源：

PROCEEDINGS ON 2014 2ND INTERNATIONAL CONFERENCE ON EMERGING TECHNOLOGY TRENDS IN ELECTRONICS, COMMUNICATION AND NETWORKING (ET2ECN) | 2014年

关键词：

Compressed sensing; OMP; Nyquist rate; Sampling;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

According to Shannon-Nyquist sampling criteria for reconstruction of information from the received signal, sampling rate must be twice or higher than signal bandwidth. But in many signal and image processing applications, due to this higher Nyquist rate too many samples are produced and compression becomes prior requirement for storage or transmission for this huge amount of data. The recent theory of Compressed Sensing is utilized to capture and represent compressible signals at a far lowest rate than the Nyquist rate. So signals can be reconstructed from critically undersampled measurements by taking advantage of their inherent low-dimensional structure. In this paper, one of the compressed sensing algorithm, namely Orthogonal Matching Pursuit (OMP) is applied to the domain of image reconstruction and its performance is evaluated at different sparsity levels and the stability of algorithms is studied in the presence of noise.

引用

页数：5

共 19 条

[1]

[Anonymous], 2006, P INT C MATH MADR SP

[2]

[Anonymous], 1928, Transactions of the American Institute of Electrical Engineers, DOI DOI 10.1109/T-AIEE.1928.5055024

[3] Iterative hard thresholding for compressed sensing [J].