dc.contributor.author | Shrestha, Bhanu | |
dc.contributor.author | Kwon, Young-Man | |
dc.contributor.author | Chung, Dong-Keun | |
dc.contributor.author | Gal, Won-Mo | |
dc.date.accessioned | 2020-03-01T00:54:11Z | |
dc.date.available | 2020-03-01T00:54:11Z | |
dc.date.issued | 2020-03-01 | |
dc.identifier.issn | 2210-142X | |
dc.identifier.uri | https://journal.uob.edu.bh:443/handle/123456789/3785 | |
dc.description.abstract | In this paper, we proposed the atrous CNN method with short computation time while maintaining a high quality of image compared to VDSR. We found that the computation was faster than VDSR by experimenting 30 times. To verify whether image quality for the proposed method is significant statistically or not, we evaluated the quality of the reconstruction image for 100 images. Through the ANOVA analysis, we found that there was no significant difference between methods in the point of PSNR view, that there was a significant difference between methods in the point of SSIM view. As a result of post-hoc analysis, there were two groups; the proposed method and VDSR, SRCNN. In conclusion, the proposed method meets our goal of maintaining image quality high and reducing computation time compared to VDSR system. | en_US |
dc.language.iso | en | en_US |
dc.publisher | University of Bahrain | en_US |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 International | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.subject | Single Image Super Resolution; Convolution Neural Network; Atrous Convolution; VDSR; SRCNN; PSNR; SSIM | en_US |
dc.title | The Atrous CNN Method with Short Computation Time for Super-Resolution | en_US |
dc.identifier.doi | http://dx.doi.org/10.12785/ijcds/090207 | |
dc.volume | 9 | en_US |
dc.issue | 2 | en_US |
dc.pagestart | 221 | en_US |
dc.pageend | 227 | en_US |
dc.contributor.authorcountry | Korea (South) | en_US |
dc.contributor.authoraffiliation | Kwangwoon University | en_US |
dc.contributor.authoraffiliation | Eulji University | en_US |
dc.source.title | International Journal of Computing and Digital Systems | en_US |
dc.abbreviatedsourcetitle | IJCDS | en_US |
The following license files are associated with this item: