Single Image Super-resolution Reconstruction Based onBidimensional Empirical Mode Decomposition
[1]MAO Xiaobo,ZHANG Zhichao.Single Image Super-resolution Reconstruction Based onBidimensional Empirical Mode Decomposition[J].Journal of Zhengzhou University (Engineering Science),2014,35(05):15-18.[doi:10.3969/i.issn.1671 -6833.2014.05.004]
Copy
Journal of Zhengzhou University (Engineering Science)[ISSN
1671-6833/CN
41-1339/T] Volume:
35卷
Number of periods:
2014 05
Page number:
15-18
Column:
Public date:
2014-09-30
- Title:
- Single Image Super-resolution Reconstruction Based onBidimensional Empirical Mode Decomposition
- Keywords:
- single image super-resolution reconstruetion; BEMD; improved kernel ridge regresslon; bicubie interpolation
- CLC:
- TP311
- DOI:
- 10.3969/i.issn.1671 -6833.2014.05.004
- Abstract:
- Aiming at the problem that most learning-based super-resolution algorithms are not eompetent totake both the reconstruction quality and eomputing speed into aecount, a novel single image super-resolutionreeonstruetion based on Bidimensional Empirical Mode Decomposition ( BEMD) is proposed. Firstly, a low.resolution image is decomposed into several layers with different complexities by BEMD, which contains vari-ous details. Then, the first lMF be reconstrueted with high frequeney details by improved kernel ridge regres.sion algorithm in order to ensure the quality of image and the other lMFs eontaining fewer details be reeonstruelby bicubie interpolation in order to improve the speed. Finally, the reeonstructed IMF’s are merged into a high.resolution image. Experimental results demonstrate that the proposed method make full use of the advantages olthe above algorithms, which not only ensure the quality of the reeonstruction image, but also improves theeomputational speed.
- References:
- -
- Similar References:
Memo
-
Last Update: