Parallel transformation of K-SVD solar image denoising algorithm

Youwen Liang; Yu Tian; Mei Li

doi:10.1117/12.2256495

28 February 2017 Parallel transformation of K-SVD solar image denoising algorithm

Youwen Liang, Yu Tian, Mei Li

Proceedings Volume 10256, Second International Conference on Photonics and Optical Engineering; 1025614 (2017) https://doi.org/10.1117/12.2256495
Event: Second International Conference on Photonics and Optical Engineering, 2016, Xi'an, China

Abstract

The images obtained by observing the sun through a large telescope always suffered with noise due to the low SNR. K-SVD denoising algorithm can effectively remove Gauss white noise. Training dictionaries for sparse representations is a time consuming task, due to the large size of the data involved and to the complexity of the training algorithms. In this paper, an OpenMP parallel programming language is proposed to transform the serial algorithm to the parallel version. Data parallelism model is used to transform the algorithm. Not one atom but multiple atoms updated simultaneously is the biggest change. The denoising effect and acceleration performance are tested after completion of the parallel algorithm. Speedup of the program is 13.563 in condition of using 16 cores. This parallel version can fully utilize the multi-core CPU hardware resources, greatly reduce running time and easily to transplant in multi-core platform.

Citation Download Citation

Youwen Liang, Yu Tian, and Mei Li "Parallel transformation of K-SVD solar image denoising algorithm", Proc. SPIE 10256, Second International Conference on Photonics and Optical Engineering, 1025614 (28 February 2017); https://doi.org/10.1117/12.2256495

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available