BoostNet: A Boosted Convolutional Neural Network for Image Blind Denoising
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Vo, Duc My | - |
dc.contributor.author | Le, Thao Phuong | - |
dc.contributor.author | Nguyen, Duc Manh | - |
dc.contributor.author | Lee, Sang-Woong | - |
dc.date.accessioned | 2021-09-02T02:40:44Z | - |
dc.date.available | 2021-09-02T02:40:44Z | - |
dc.date.created | 2021-06-11 | - |
dc.date.issued | 2021-05 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/82013 | - |
dc.description.abstract | Deep convolutional neural networks and generative adversarial networks currently attracted the attention of researchers because it is more effective than conventional representation-based methods. However, they have been facing two serious problems in the trade-off between noise removal, artifacts, and preserving low-contrast features and high-frequency details. In particular, deep convolutional neural networks might fail to remove strong noise in regions with higher noise levels while completely erasing low-contrast features and high-frequency details. By contrast, compared with conventional deep convolutional neural networks, generative adversarial networks might be better in balancing between erasing different types of noise and recovering texture details. However, they often generate fake details and unexpected artifacts in the image owing to the instability of their discriminator during training. In this study, we explored an innovative strategy for handling the serious problems of image denoising. With this strategy, we propose a novel boosting generative adversarial network (BoostNet) that not only combines all advantages of a generative adversarial sub-network and a deep convolutional neural network, it also successfully avoids the serious problems caused by the corruption and instability of training. BoostNet is developed by integrating a stand-alone deep convolutional neural network and a robust generative adversarial network into an ensemble network, which can effectively boost the denoising performance. We conducted several experiments using challenging datasets of additive white Gaussian noise and real-world noisy images. The experimental results show that our proposed method is superior to other state-of-the-art denoisers in terms of quantitative metrics and visual quality. Our source codes and datasets for BoostNet are available at https://github.com/ZeroZero19/BoostNet.git. CCBY | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.relation.isPartOf | IEEE Access | - |
dc.title | BoostNet: A Boosted Convolutional Neural Network for Image Blind Denoising | - |
dc.type | Article | - |
dc.type.rims | ART | - |
dc.description.journalClass | 1 | - |
dc.identifier.wosid | 000688230700001 | - |
dc.identifier.doi | 10.1109/ACCESS.2021.3081697 | - |
dc.identifier.bibliographicCitation | IEEE Access, v.9, pp.115145 - 115164 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-85107220412 | - |
dc.citation.endPage | 115164 | - |
dc.citation.startPage | 115145 | - |
dc.citation.title | IEEE Access | - |
dc.citation.volume | 9 | - |
dc.contributor.affiliatedAuthor | Vo, Duc My | - |
dc.contributor.affiliatedAuthor | Lee, Sang-Woong | - |
dc.type.docType | Article in Press | - |
dc.subject.keywordAuthor | blind denoising | - |
dc.subject.keywordAuthor | BoostNet | - |
dc.subject.keywordAuthor | Convolutional neural networks | - |
dc.subject.keywordAuthor | deep convolutional neural networks | - |
dc.subject.keywordAuthor | Drosophila | - |
dc.subject.keywordAuthor | fluorescence microscopy images | - |
dc.subject.keywordAuthor | Generative adversarial networks | - |
dc.subject.keywordAuthor | Generative adversarial networks | - |
dc.subject.keywordAuthor | Generators | - |
dc.subject.keywordAuthor | image denoising | - |
dc.subject.keywordAuthor | Noise measurement | - |
dc.subject.keywordAuthor | Noise reduction | - |
dc.subject.keywordAuthor | PSNR | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordPlus | Convolution | - |
dc.subject.keywordPlus | Deep neural networks | - |
dc.subject.keywordPlus | Economic and social effects | - |
dc.subject.keywordPlus | Gaussian noise (electronic) | - |
dc.subject.keywordPlus | Image denoising | - |
dc.subject.keywordPlus | Textures | - |
dc.subject.keywordPlus | White noise | - |
dc.subject.keywordPlus | Additive White Gaussian noise | - |
dc.subject.keywordPlus | Adversarial networks | - |
dc.subject.keywordPlus | Ensemble networks | - |
dc.subject.keywordPlus | High frequency HF | - |
dc.subject.keywordPlus | Higher noise levels | - |
dc.subject.keywordPlus | Innovative strategies | - |
dc.subject.keywordPlus | Quantitative metrics | - |
dc.subject.keywordPlus | State of the art | - |
dc.subject.keywordPlus | Convolutional neural networks | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
1342, Seongnam-daero, Sujeong-gu, Seongnam-si, Gyeonggi-do, Republic of Korea(13120)031-750-5114
COPYRIGHT 2020 Gachon University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.