Single Image Super-Resolution Reconstruction Method for Generative Adversarial Network
The super-resolution reconstruction method based on deep convolutional neural network has a high peak signal-to-noise ratio (PSNR), but the reconstruction results have the problem of lack of high-frequency information and texture details and poor visual perception under large-scale factors. Aiming a...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2020-09-01
|
| Series: | Jisuanji kexue yu tansuo |
| Subjects: | |
| Online Access: | http://fcst.ceaj.org/CN/abstract/abstract2366.shtml |
| _version_ | 1819112392675557376 |
|---|---|
| author | PENG Yanfei, GAO Yi, DU Tingting, SANG Yu, ZI Lingling |
| author_facet | PENG Yanfei, GAO Yi, DU Tingting, SANG Yu, ZI Lingling |
| author_sort | PENG Yanfei, GAO Yi, DU Tingting, SANG Yu, ZI Lingling |
| collection | DOAJ |
| description | The super-resolution reconstruction method based on deep convolutional neural network has a high peak signal-to-noise ratio (PSNR), but the reconstruction results have the problem of lack of high-frequency information and texture details and poor visual perception under large-scale factors. Aiming at this problem, a single image super-resolution reconstruction method based on generative adversarial network is proposed. Firstly, the hinge loss in the migration support vector machine is taken as the objective function, and then the Charbonnier loss which is more stable and more anti-noise is used instead of the L2 loss function. Finally, the batch normalization layer which is unfavorable to the super resolution of the image in the residual block and discriminator is removed, and the spectral normalization is used in the generator and discriminator to reduce the computational overhead and stabilize the model training. The experimental results of 4X upscaling show that compared with other comparison methods, the PSNR value of the reconstructed image is improved by up to 4.6 dB and the SSIM value is increased by 0.1, and the test time is shorter. The experimental data and effect diagram show that the super-resolution image reconstructed by this method has better visual effect and higher PSNR and SSIM values. |
| first_indexed | 2024-12-22T04:12:47Z |
| format | Article |
| id | doaj.art-9f85062f07f6472ba3db24f6b5c4c095 |
| institution | Directory Open Access Journal |
| issn | 1673-9418 |
| language | zho |
| last_indexed | 2024-12-22T04:12:47Z |
| publishDate | 2020-09-01 |
| publisher | Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press |
| record_format | Article |
| series | Jisuanji kexue yu tansuo |
| spelling | doaj.art-9f85062f07f6472ba3db24f6b5c4c0952022-12-21T18:39:29ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182020-09-011491612162010.3778/j.issn.1673-9418.1910067Single Image Super-Resolution Reconstruction Method for Generative Adversarial NetworkPENG Yanfei, GAO Yi, DU Tingting, SANG Yu, ZI Lingling0School of Electronic and Information Engineering, Liaoning Technical University, Huludao, Liaoning 125105, ChinaThe super-resolution reconstruction method based on deep convolutional neural network has a high peak signal-to-noise ratio (PSNR), but the reconstruction results have the problem of lack of high-frequency information and texture details and poor visual perception under large-scale factors. Aiming at this problem, a single image super-resolution reconstruction method based on generative adversarial network is proposed. Firstly, the hinge loss in the migration support vector machine is taken as the objective function, and then the Charbonnier loss which is more stable and more anti-noise is used instead of the L2 loss function. Finally, the batch normalization layer which is unfavorable to the super resolution of the image in the residual block and discriminator is removed, and the spectral normalization is used in the generator and discriminator to reduce the computational overhead and stabilize the model training. The experimental results of 4X upscaling show that compared with other comparison methods, the PSNR value of the reconstructed image is improved by up to 4.6 dB and the SSIM value is increased by 0.1, and the test time is shorter. The experimental data and effect diagram show that the super-resolution image reconstructed by this method has better visual effect and higher PSNR and SSIM values.http://fcst.ceaj.org/CN/abstract/abstract2366.shtmlsuper-resolution reconstructiongenerative adversarial network (gan)deep learningconvolutional neural network (cnn)loss function |
| spellingShingle | PENG Yanfei, GAO Yi, DU Tingting, SANG Yu, ZI Lingling Single Image Super-Resolution Reconstruction Method for Generative Adversarial Network Jisuanji kexue yu tansuo super-resolution reconstruction generative adversarial network (gan) deep learning convolutional neural network (cnn) loss function |
| title | Single Image Super-Resolution Reconstruction Method for Generative Adversarial Network |
| title_full | Single Image Super-Resolution Reconstruction Method for Generative Adversarial Network |
| title_fullStr | Single Image Super-Resolution Reconstruction Method for Generative Adversarial Network |
| title_full_unstemmed | Single Image Super-Resolution Reconstruction Method for Generative Adversarial Network |
| title_short | Single Image Super-Resolution Reconstruction Method for Generative Adversarial Network |
| title_sort | single image super resolution reconstruction method for generative adversarial network |
| topic | super-resolution reconstruction generative adversarial network (gan) deep learning convolutional neural network (cnn) loss function |
| url | http://fcst.ceaj.org/CN/abstract/abstract2366.shtml |
| work_keys_str_mv | AT pengyanfeigaoyidutingtingsangyuzilingling singleimagesuperresolutionreconstructionmethodforgenerativeadversarialnetwork |