Boosting of Denoising Effect with Fusion Strategy
Image denoising, a fundamental step in image processing, has been widely studied for several decades. Denoising methods can be classified as internal or external depending on whether they exploit the internal prior or the external noisy-clean image priors to reconstruct a latent image. Typically, th...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/11/3857 |
| _version_ | 1797566381742358528 |
|---|---|
| author | Fangjia Yang Shaoping Xu Chongxi Li |
| author_facet | Fangjia Yang Shaoping Xu Chongxi Li |
| author_sort | Fangjia Yang |
| collection | DOAJ |
| description | Image denoising, a fundamental step in image processing, has been widely studied for several decades. Denoising methods can be classified as internal or external depending on whether they exploit the internal prior or the external noisy-clean image priors to reconstruct a latent image. Typically, these two kinds of methods have their respective merits and demerits. Using a single denoising model to improve existing methods remains a challenge. In this paper, we propose a method for boosting the denoising effect via the image fusion strategy. This study aims to boost the performance of two typical denoising methods, the nonlocally centralized sparse representation (NCSR) and residual learning of deep CNN (DnCNN). These two methods have complementary strengths and can be chosen to represent internal and external denoising methods, respectively. The boosting process is formulated as an adaptive weight-based image fusion problem by preserving the details for the initial denoised images output by the NCSR and the DnCNN. Specifically, we design two kinds of weights to adaptively reflect the influence of the pixel intensity changes and the global gradient of the initial denoised images. A linear combination of these two kinds of weights determines the final weight. The initial denoised images are integrated into the fusion framework to achieve our denoising results. Extensive experiments show that the proposed method significantly outperforms the NCSR and the DnCNN both quantitatively and visually when they are considered as individual methods; similarly, it outperforms several other state-of-the-art denoising methods. |
| first_indexed | 2024-03-10T19:26:58Z |
| format | Article |
| id | doaj.art-9c015e50d165433ab9b00ebb757d41fb |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T19:26:58Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-9c015e50d165433ab9b00ebb757d41fb2023-11-20T02:30:34ZengMDPI AGApplied Sciences2076-34172020-06-011011385710.3390/app10113857Boosting of Denoising Effect with Fusion StrategyFangjia Yang0Shaoping Xu1Chongxi Li2School of Information Engineering, Nanchang University, Nanchang 330031, ChinaSchool of Information Engineering, Nanchang University, Nanchang 330031, ChinaSchool of Information Engineering, Nanchang University, Nanchang 330031, ChinaImage denoising, a fundamental step in image processing, has been widely studied for several decades. Denoising methods can be classified as internal or external depending on whether they exploit the internal prior or the external noisy-clean image priors to reconstruct a latent image. Typically, these two kinds of methods have their respective merits and demerits. Using a single denoising model to improve existing methods remains a challenge. In this paper, we propose a method for boosting the denoising effect via the image fusion strategy. This study aims to boost the performance of two typical denoising methods, the nonlocally centralized sparse representation (NCSR) and residual learning of deep CNN (DnCNN). These two methods have complementary strengths and can be chosen to represent internal and external denoising methods, respectively. The boosting process is formulated as an adaptive weight-based image fusion problem by preserving the details for the initial denoised images output by the NCSR and the DnCNN. Specifically, we design two kinds of weights to adaptively reflect the influence of the pixel intensity changes and the global gradient of the initial denoised images. A linear combination of these two kinds of weights determines the final weight. The initial denoised images are integrated into the fusion framework to achieve our denoising results. Extensive experiments show that the proposed method significantly outperforms the NCSR and the DnCNN both quantitatively and visually when they are considered as individual methods; similarly, it outperforms several other state-of-the-art denoising methods.https://www.mdpi.com/2076-3417/10/11/3857image denoisingdenoising effectboostingimage fusionpixel intensityglobal gradient |
| spellingShingle | Fangjia Yang Shaoping Xu Chongxi Li Boosting of Denoising Effect with Fusion Strategy Applied Sciences image denoising denoising effect boosting image fusion pixel intensity global gradient |
| title | Boosting of Denoising Effect with Fusion Strategy |
| title_full | Boosting of Denoising Effect with Fusion Strategy |
| title_fullStr | Boosting of Denoising Effect with Fusion Strategy |
| title_full_unstemmed | Boosting of Denoising Effect with Fusion Strategy |
| title_short | Boosting of Denoising Effect with Fusion Strategy |
| title_sort | boosting of denoising effect with fusion strategy |
| topic | image denoising denoising effect boosting image fusion pixel intensity global gradient |
| url | https://www.mdpi.com/2076-3417/10/11/3857 |
| work_keys_str_mv | AT fangjiayang boostingofdenoisingeffectwithfusionstrategy AT shaopingxu boostingofdenoisingeffectwithfusionstrategy AT chongxili boostingofdenoisingeffectwithfusionstrategy |