Super-Resolution Reconstruction of Astronomical Images Based on Centralized Sparse Representation

Yakang Duan; Lin Luo; Jinlong Li; Xiaorong Gao

doi:10.3788/LOP56.221004

Laser & Optoelectronics Progress, Volume. 56, Issue 22, 221004(2019)

Super-Resolution Reconstruction of Astronomical Images Based on Centralized Sparse Representation

Yakang Duan, Lin Luo, Jinlong Li^*, and Xiaorong Gao

Author Affiliations

School of Physical Science and Technology, Southwest Jiaotong University, Chengdu, Sichuan 610031, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(9)

Fig. 1. Flowchart of agglomerative hierarchical clustering

Download full size

Fig. 2. Hierarchical clustering tree

Download full size

Fig. 3. Test image set. (a) Cluster; (b) Galaxy; (c) Jupiter; (d) Satellite; (e) Saturn

Download full size

Fig. 4. Effects of different experimental parameters on reconstruction results. (a) Clustering number; (b) γ

Download full size

Fig. 5. Super-resolution reconstruction results of Satellite with scale factor of 3. (a) Original image; (b) bicubic interpolation algorithm; (c) ScSR algorithm; (d) Zeyde algorithm; (e) ANR algorithm; (f) ASDS algorithm; (g) NCSR algorithm; (h) proposed algorithm

Download full size

Fig. 6. Super-resolution reconstruction results of Saturn with scale factor of 3. (a) Original image; (b) bicubic interpolation algorithm; (c) ScSR algorithm; (d) Zeyde algorithm; (e) ANR algorithm; (f) ASDS algorithm; (g) NCSR algorithm; (h) proposed algorithm

Download full size

Table 1. Comparison of PSNR of reconstructed images obtained by different methodsdB

View table

Table 1. Comparison of PSNR of reconstructed images obtained by different methodsdB

Image	Bicubic	ScSR	Zeyde	ANR	ASDS	NCSR	Proposed method
Cluster	25.64	26.81	28.36	28.27	28.45	28.97	29.12
Galaxy	33.57	35.37	37.38	37.24	37.33	38.15	38.35
Jupiter	31.74	34.25	35.20	35.36	35.72	36.05	36.06
Satellite	28.17	33.19	34.07	34.50	37.31	37.46	37.69
Saturn	27.24	31.30	32.99	32.35	34.07	34.23	34.51
Average	29.28	32.18	33.60	33.54	34.58	34.97	35.15

Table 2. Comparison of SSIM of reconstructed images obtained by different methods

View table

Table 2. Comparison of SSIM of reconstructed images obtained by different methods

Image	Bicubic	ScSR	Zeyde	ANR	ASDS	NCSR	Proposed method
Cluster	0.6578	0.6618	0.7633	0.7624	0.7727	0.7913	0.7999
Galaxy	0.9062	0.9027	0.9412	0.9401	0.9394	0.9471	0.9505
Jupiter	0.8824	0.9058	0.9246	0.9274	0.9298	0.9357	0.9362
Satellite	0.9428	0.9470	0.9738	0.9742	0.9857	0.9877	0.9885
Saturn	0.9403	0.9245	0.9703	0.9614	0.9797	0.9787	0.9807
Average	0.8659	0.8684	0.9146	0.9131	0.9215	0.9281	0.9312

Table 3. Comparison of reconstruction time of different methodss
View table
Table 3. Comparison of reconstruction time of different methodss
Image ANR ASDS NCSR Proposed method
Cluster 0.3 190.2 355.5 362.5
Galaxy 0.3 157.2 337.3 348.3
Jupiter 0.6 331.7 702.4 680.3
Satellite 0.7 374.8 681.4 665.8
Saturn 0.3 183.1 348.8 335.6
Average 0.4 247.4 485.1 478.5

Tools

Get Citation

Copy Citation Text

Yakang Duan, Lin Luo, Jinlong Li, Xiaorong Gao. Super-Resolution Reconstruction of Astronomical Images Based on Centralized Sparse Representation[J]. Laser & Optoelectronics Progress, 2019, 56(22): 221004

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Image Processing

Received: Apr. 12, 2019

Accepted: May. 17, 2019

Published Online: Nov. 9, 2019

The Author Email: Li Jinlong (jinlong_lee@126.com)

DOI:10.3788/LOP56.221004

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Comparison of PSNR of reconstructed images obtained by different methodsdB

Table 1. Comparison of PSNR of reconstructed images obtained by different methodsdB

Table 2. Comparison of SSIM of reconstructed images obtained by different methods

Table 2. Comparison of SSIM of reconstructed images obtained by different methods

Table 3. Comparison of reconstruction time of different methodss

Table 3. Comparison of reconstruction time of different methodss