EFID: Edge-Focused Image Denoising Using a Convolutional Neural Network
In this paper, we propose an edge-focused image denoising convolutional neural network for the restoration of noisy images corrupted with additive white Gaussian noise (AWGN). First, the edge information for an input image is obtained for each RGB channel using the simple Laplacian edge operator on...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10025731/ |
| _version_ | 1811170581418082304 |
|---|---|
| author | Shivarama Holla K Nokap Park Bumshik Lee |
| author_facet | Shivarama Holla K Nokap Park Bumshik Lee |
| author_sort | Shivarama Holla K |
| collection | DOAJ |
| description | In this paper, we propose an edge-focused image denoising convolutional neural network for the restoration of noisy images corrupted with additive white Gaussian noise (AWGN). First, the edge information for an input image is obtained for each RGB channel using the simple Laplacian edge operator on a smoothened image using the smoothen mask. Second, residual convolutional blocks, where each block comprises two parallel depth layers (one for an image channel and the other for respective edge channels), perform image and edge processing. Finally, the processed image and edge features are mixed and mapped using a single convolutional layer into the restored image. Our proposed parallel image and edge processing blocks can recover edges and fine structures while smoothing out the noise. In addition, our proposed network is efficiently designed such that the total number of weight parameters can be considerably reduced compared with conventional methods. Experimental results show that the proposed model is more effective in preserving textures and edges while removing noise and achieves up to 0.8 dB higher PSNR and 0.05 higher SSIM on a real image dataset than conventional methods. |
| first_indexed | 2024-04-10T17:00:05Z |
| format | Article |
| id | doaj.art-d4b140dbe5a04a519ddcf7f307471747 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T17:00:05Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d4b140dbe5a04a519ddcf7f3074717472023-02-07T00:00:52ZengIEEEIEEE Access2169-35362023-01-01119613962610.1109/ACCESS.2023.323983510025731EFID: Edge-Focused Image Denoising Using a Convolutional Neural NetworkShivarama Holla K0https://orcid.org/0000-0003-2648-6531Nokap Park1https://orcid.org/0000-0001-7971-9461Bumshik Lee2https://orcid.org/0000-0003-2482-1869Department of Information and Communication Engineering, Chosun University, Gwangju, South KoreaSK Telecom, Seoul, South KoreaDepartment of Information and Communication Engineering, Chosun University, Gwangju, South KoreaIn this paper, we propose an edge-focused image denoising convolutional neural network for the restoration of noisy images corrupted with additive white Gaussian noise (AWGN). First, the edge information for an input image is obtained for each RGB channel using the simple Laplacian edge operator on a smoothened image using the smoothen mask. Second, residual convolutional blocks, where each block comprises two parallel depth layers (one for an image channel and the other for respective edge channels), perform image and edge processing. Finally, the processed image and edge features are mixed and mapped using a single convolutional layer into the restored image. Our proposed parallel image and edge processing blocks can recover edges and fine structures while smoothing out the noise. In addition, our proposed network is efficiently designed such that the total number of weight parameters can be considerably reduced compared with conventional methods. Experimental results show that the proposed model is more effective in preserving textures and edges while removing noise and achieves up to 0.8 dB higher PSNR and 0.05 higher SSIM on a real image dataset than conventional methods.https://ieeexplore.ieee.org/document/10025731/Convolutional neural networksdeep learningdenoisingedge guidanceGaussian noise |
| spellingShingle | Shivarama Holla K Nokap Park Bumshik Lee EFID: Edge-Focused Image Denoising Using a Convolutional Neural Network IEEE Access Convolutional neural networks deep learning denoising edge guidance Gaussian noise |
| title | EFID: Edge-Focused Image Denoising Using a Convolutional Neural Network |
| title_full | EFID: Edge-Focused Image Denoising Using a Convolutional Neural Network |
| title_fullStr | EFID: Edge-Focused Image Denoising Using a Convolutional Neural Network |
| title_full_unstemmed | EFID: Edge-Focused Image Denoising Using a Convolutional Neural Network |
| title_short | EFID: Edge-Focused Image Denoising Using a Convolutional Neural Network |
| title_sort | efid edge focused image denoising using a convolutional neural network |
| topic | Convolutional neural networks deep learning denoising edge guidance Gaussian noise |
| url | https://ieeexplore.ieee.org/document/10025731/ |
| work_keys_str_mv | AT shivaramahollak efidedgefocusedimagedenoisingusingaconvolutionalneuralnetwork AT nokappark efidedgefocusedimagedenoisingusingaconvolutionalneuralnetwork AT bumshiklee efidedgefocusedimagedenoisingusingaconvolutionalneuralnetwork |