Residual Forward-Subtracted U-Shaped Network for Dynamic and Static Image Restoration
Advanced image sensors with high resolution are now being developed for specially purposed electro-optical systems, with research focused on robust image quality performance in terms of super resolution and noise removal under various environmental conditions. Recently, machine-learning and deep-lea...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9146538/ |
| _version_ | 1818579412225884160 |
|---|---|
| author | Ho Min Jung Byeong Hak Kim Min Young Kim |
| author_facet | Ho Min Jung Byeong Hak Kim Min Young Kim |
| author_sort | Ho Min Jung |
| collection | DOAJ |
| description | Advanced image sensors with high resolution are now being developed for specially purposed electro-optical systems, with research focused on robust image quality performance in terms of super resolution and noise removal under various environmental conditions. Recently, machine-learning and deep-learning methods have been studied as the best practical techniques for restoration to improve the deteriorated image quality of sensors. However, these methods show limitations and side effects of image degradation such as image non-uniformity. In this paper, we analyze and randomly generate additive white Gaussian noise, non-uniform line noise, and dark saturation as representative image degradations. We then propose an advanced U-net model based on global and local residual learning in order to restore complexly deteriorated images. The proposed method shows unparalleled performance compared to alternative models and previous studies. In particular, various complex noise components are minimized and improved with equal quality so that variation between sequential images is minimized. These findings leverage mutual corroboration of quantitative and qualitative evaluation metrics. In the future, the proposed model is expected to contribute to a wide range of field applications such as defense, surveillance, and video media for image quality enhancement technologies. |
| first_indexed | 2024-12-16T07:01:17Z |
| format | Article |
| id | doaj.art-3e2ddd58957747279ee65601051b6fba |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T07:01:17Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3e2ddd58957747279ee65601051b6fba2022-12-21T22:40:09ZengIEEEIEEE Access2169-35362020-01-01814540114541210.1109/ACCESS.2020.30115809146538Residual Forward-Subtracted U-Shaped Network for Dynamic and Static Image RestorationHo Min Jung0https://orcid.org/0000-0003-2326-6584Byeong Hak Kim1https://orcid.org/0000-0002-2798-7154Min Young Kim2https://orcid.org/0000-0001-7263-3403School of Electronics Engineering, Kyungpook National University, Daegu, South KoreaHanwha Systems Company, Gumi, South KoreaSchool of Electronics Engineering, Kyungpook National University, Daegu, South KoreaAdvanced image sensors with high resolution are now being developed for specially purposed electro-optical systems, with research focused on robust image quality performance in terms of super resolution and noise removal under various environmental conditions. Recently, machine-learning and deep-learning methods have been studied as the best practical techniques for restoration to improve the deteriorated image quality of sensors. However, these methods show limitations and side effects of image degradation such as image non-uniformity. In this paper, we analyze and randomly generate additive white Gaussian noise, non-uniform line noise, and dark saturation as representative image degradations. We then propose an advanced U-net model based on global and local residual learning in order to restore complexly deteriorated images. The proposed method shows unparalleled performance compared to alternative models and previous studies. In particular, various complex noise components are minimized and improved with equal quality so that variation between sequential images is minimized. These findings leverage mutual corroboration of quantitative and qualitative evaluation metrics. In the future, the proposed model is expected to contribute to a wide range of field applications such as defense, surveillance, and video media for image quality enhancement technologies.https://ieeexplore.ieee.org/document/9146538/Restorationmulti-type noisesimage denoisingimage enhancementconvolutional neural networkresidual learning |
| spellingShingle | Ho Min Jung Byeong Hak Kim Min Young Kim Residual Forward-Subtracted U-Shaped Network for Dynamic and Static Image Restoration IEEE Access Restoration multi-type noises image denoising image enhancement convolutional neural network residual learning |
| title | Residual Forward-Subtracted U-Shaped Network for Dynamic and Static Image Restoration |
| title_full | Residual Forward-Subtracted U-Shaped Network for Dynamic and Static Image Restoration |
| title_fullStr | Residual Forward-Subtracted U-Shaped Network for Dynamic and Static Image Restoration |
| title_full_unstemmed | Residual Forward-Subtracted U-Shaped Network for Dynamic and Static Image Restoration |
| title_short | Residual Forward-Subtracted U-Shaped Network for Dynamic and Static Image Restoration |
| title_sort | residual forward subtracted u shaped network for dynamic and static image restoration |
| topic | Restoration multi-type noises image denoising image enhancement convolutional neural network residual learning |
| url | https://ieeexplore.ieee.org/document/9146538/ |
| work_keys_str_mv | AT hominjung residualforwardsubtractedushapednetworkfordynamicandstaticimagerestoration AT byeonghakkim residualforwardsubtractedushapednetworkfordynamicandstaticimagerestoration AT minyoungkim residualforwardsubtractedushapednetworkfordynamicandstaticimagerestoration |