A Multi-Scale Feature Extraction-Based Normalized Attention Neural Network for Image Denoising
Due to the rapid development of deep learning and artificial intelligence techniques, denoising via neural networks has drawn great attention due to their flexibility and excellent performances. However, for most convolutional network denoising methods, the convolution kernel is only one layer deep,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/3/319 |
| _version_ | 1797405888724598784 |
|---|---|
| author | Yi Wang Xiao Song Guanghong Gong Ni Li |
| author_facet | Yi Wang Xiao Song Guanghong Gong Ni Li |
| author_sort | Yi Wang |
| collection | DOAJ |
| description | Due to the rapid development of deep learning and artificial intelligence techniques, denoising via neural networks has drawn great attention due to their flexibility and excellent performances. However, for most convolutional network denoising methods, the convolution kernel is only one layer deep, and features of distinct scales are neglected. Moreover, in the convolution operation, all channels are treated equally; the relationships of channels are not considered. In this paper, we propose a multi-scale feature extraction-based normalized attention neural network (MFENANN) for image denoising. In MFENANN, we define a multi-scale feature extraction block to extract and combine features at distinct scales of the noisy image. In addition, we propose a normalized attention network (NAN) to learn the relationships between channels, which smooths the optimization landscape and speeds up the convergence process for training an attention model. Moreover, we introduce the NAN to convolutional network denoising, in which each channel gets gain; channels can play different roles in the subsequent convolution. To testify the effectiveness of the proposed MFENANN, we used both grayscale and color image sets whose noise levels ranged from 0 to 75 to do the experiments. The experimental results show that compared with some state-of-the-art denoising methods, the restored images of MFENANN have larger peak signal-to-noise ratios (PSNR) and structural similarity index measure (SSIM) values and get better overall appearance. |
| first_indexed | 2024-03-09T03:17:43Z |
| format | Article |
| id | doaj.art-311147bef8e144c59a0ccb7f4346f9e3 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T03:17:43Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-311147bef8e144c59a0ccb7f4346f9e32023-12-03T15:16:36ZengMDPI AGElectronics2079-92922021-01-0110331910.3390/electronics10030319A Multi-Scale Feature Extraction-Based Normalized Attention Neural Network for Image DenoisingYi Wang0Xiao Song1Guanghong Gong2Ni Li3School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, ChinaSchool of Cyber Science and Technology, Beihang University, Beijing 100191, ChinaSchool of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, ChinaSchool of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, ChinaDue to the rapid development of deep learning and artificial intelligence techniques, denoising via neural networks has drawn great attention due to their flexibility and excellent performances. However, for most convolutional network denoising methods, the convolution kernel is only one layer deep, and features of distinct scales are neglected. Moreover, in the convolution operation, all channels are treated equally; the relationships of channels are not considered. In this paper, we propose a multi-scale feature extraction-based normalized attention neural network (MFENANN) for image denoising. In MFENANN, we define a multi-scale feature extraction block to extract and combine features at distinct scales of the noisy image. In addition, we propose a normalized attention network (NAN) to learn the relationships between channels, which smooths the optimization landscape and speeds up the convergence process for training an attention model. Moreover, we introduce the NAN to convolutional network denoising, in which each channel gets gain; channels can play different roles in the subsequent convolution. To testify the effectiveness of the proposed MFENANN, we used both grayscale and color image sets whose noise levels ranged from 0 to 75 to do the experiments. The experimental results show that compared with some state-of-the-art denoising methods, the restored images of MFENANN have larger peak signal-to-noise ratios (PSNR) and structural similarity index measure (SSIM) values and get better overall appearance.https://www.mdpi.com/2079-9292/10/3/319image denoisingattention neural networkmulti-scale feature extractionPSNRSSIM |
| spellingShingle | Yi Wang Xiao Song Guanghong Gong Ni Li A Multi-Scale Feature Extraction-Based Normalized Attention Neural Network for Image Denoising Electronics image denoising attention neural network multi-scale feature extraction PSNR SSIM |
| title | A Multi-Scale Feature Extraction-Based Normalized Attention Neural Network for Image Denoising |
| title_full | A Multi-Scale Feature Extraction-Based Normalized Attention Neural Network for Image Denoising |
| title_fullStr | A Multi-Scale Feature Extraction-Based Normalized Attention Neural Network for Image Denoising |
| title_full_unstemmed | A Multi-Scale Feature Extraction-Based Normalized Attention Neural Network for Image Denoising |
| title_short | A Multi-Scale Feature Extraction-Based Normalized Attention Neural Network for Image Denoising |
| title_sort | multi scale feature extraction based normalized attention neural network for image denoising |
| topic | image denoising attention neural network multi-scale feature extraction PSNR SSIM |
| url | https://www.mdpi.com/2079-9292/10/3/319 |
| work_keys_str_mv | AT yiwang amultiscalefeatureextractionbasednormalizedattentionneuralnetworkforimagedenoising AT xiaosong amultiscalefeatureextractionbasednormalizedattentionneuralnetworkforimagedenoising AT guanghonggong amultiscalefeatureextractionbasednormalizedattentionneuralnetworkforimagedenoising AT nili amultiscalefeatureextractionbasednormalizedattentionneuralnetworkforimagedenoising AT yiwang multiscalefeatureextractionbasednormalizedattentionneuralnetworkforimagedenoising AT xiaosong multiscalefeatureextractionbasednormalizedattentionneuralnetworkforimagedenoising AT guanghonggong multiscalefeatureextractionbasednormalizedattentionneuralnetworkforimagedenoising AT nili multiscalefeatureextractionbasednormalizedattentionneuralnetworkforimagedenoising |