Deep Residual Network with Sparse Feedback for Image Restoration
A deep neural network is difficult to train due to a large number of unknown parameters. To increase trainable performance, we present a moderate depth residual network for the restoration of motion blurring and noisy images. The proposed network has only 10 layers, and the sparse feedbacks are adde...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/8/12/2417 |
| _version_ | 1817980141906690048 |
|---|---|
| author | Zhenyu Guo Yujuan Sun Muwei Jian Xiaofeng Zhang |
| author_facet | Zhenyu Guo Yujuan Sun Muwei Jian Xiaofeng Zhang |
| author_sort | Zhenyu Guo |
| collection | DOAJ |
| description | A deep neural network is difficult to train due to a large number of unknown parameters. To increase trainable performance, we present a moderate depth residual network for the restoration of motion blurring and noisy images. The proposed network has only 10 layers, and the sparse feedbacks are added in the middle and the last layers, which are called FbResNet. FbResNet has fast convergence speed and effective denoising performance. In addition, it can also reduce the artificial Mosaic trace at the seam of patches, and visually pleasant output results can be produced from the blurred images or noisy images. Experimental results show the effectiveness of our designed model and method. |
| first_indexed | 2024-04-13T22:50:43Z |
| format | Article |
| id | doaj.art-dc92351cae99499197c06d4804f544d6 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-13T22:50:43Z |
| publishDate | 2018-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-dc92351cae99499197c06d4804f544d62022-12-22T02:26:13ZengMDPI AGApplied Sciences2076-34172018-11-01812241710.3390/app8122417app8122417Deep Residual Network with Sparse Feedback for Image RestorationZhenyu Guo0Yujuan Sun1Muwei Jian2Xiaofeng Zhang3School of Information and Electrical Engineering, Ludong University, Yantai 264025, ChinaSchool of Information and Electrical Engineering, Ludong University, Yantai 264025, ChinaSchool of Computer Science and Technology, Shandong University of Finance and Economics, Jinan 250014, ChinaSchool of Information and Electrical Engineering, Ludong University, Yantai 264025, ChinaA deep neural network is difficult to train due to a large number of unknown parameters. To increase trainable performance, we present a moderate depth residual network for the restoration of motion blurring and noisy images. The proposed network has only 10 layers, and the sparse feedbacks are added in the middle and the last layers, which are called FbResNet. FbResNet has fast convergence speed and effective denoising performance. In addition, it can also reduce the artificial Mosaic trace at the seam of patches, and visually pleasant output results can be produced from the blurred images or noisy images. Experimental results show the effectiveness of our designed model and method.https://www.mdpi.com/2076-3417/8/12/2417image restorationmotion deburringimage denoisingsparse feedback |
| spellingShingle | Zhenyu Guo Yujuan Sun Muwei Jian Xiaofeng Zhang Deep Residual Network with Sparse Feedback for Image Restoration Applied Sciences image restoration motion deburring image denoising sparse feedback |
| title | Deep Residual Network with Sparse Feedback for Image Restoration |
| title_full | Deep Residual Network with Sparse Feedback for Image Restoration |
| title_fullStr | Deep Residual Network with Sparse Feedback for Image Restoration |
| title_full_unstemmed | Deep Residual Network with Sparse Feedback for Image Restoration |
| title_short | Deep Residual Network with Sparse Feedback for Image Restoration |
| title_sort | deep residual network with sparse feedback for image restoration |
| topic | image restoration motion deburring image denoising sparse feedback |
| url | https://www.mdpi.com/2076-3417/8/12/2417 |
| work_keys_str_mv | AT zhenyuguo deepresidualnetworkwithsparsefeedbackforimagerestoration AT yujuansun deepresidualnetworkwithsparsefeedbackforimagerestoration AT muweijian deepresidualnetworkwithsparsefeedbackforimagerestoration AT xiaofengzhang deepresidualnetworkwithsparsefeedbackforimagerestoration |