Multi-Level Wavelet-Based Network Embedded with Edge Enhancement Information for Underwater Image Enhancement
As an image processing method, underwater image enhancement (UIE) plays an important role in the field of underwater resource detection and engineering research. Currently, the convolutional neural network (CNN)- and Transformer-based methods are the mainstream methods for UIE. However, CNNs usually...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/10/7/884 |
| _version_ | 1827596866263449600 |
|---|---|
| author | Kaichuan Sun Fei Meng Yubo Tian |
| author_facet | Kaichuan Sun Fei Meng Yubo Tian |
| author_sort | Kaichuan Sun |
| collection | DOAJ |
| description | As an image processing method, underwater image enhancement (UIE) plays an important role in the field of underwater resource detection and engineering research. Currently, the convolutional neural network (CNN)- and Transformer-based methods are the mainstream methods for UIE. However, CNNs usually use pooling to expand the receptive field, which may lead to information loss that is not conducive to feature extraction and analysis. At the same time, edge blurring can easily occur in enhanced images obtained by the existing methods. To address this issue, this paper proposes a framework that combines CNN and Transformer, employs the wavelet transform and inverse wavelet transform for encoding and decoding, and progressively embeds the edge information on the raw image in the encoding process. Specifically, first, features of the raw image and its edge detection image are extracted step by step using the convolution module and the residual dense attention module, respectively, to obtain mixed feature maps of different resolutions. Next, the residual structure Swin Transformer group is used to extract global features. Then, the resulting feature map and the encoder’s hybrid feature map are used for high-resolution feature map reconstruction by the decoder. The experimental results show that the proposed method can achieve an excellent effect in edge information protection and visual reconstruction of images. In addition, the effectiveness of each component of the proposed model is verified by ablation experiments. |
| first_indexed | 2024-03-09T03:17:34Z |
| format | Article |
| id | doaj.art-04c439b3c9014c1c94f1c882e45c25e9 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-09T03:17:34Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-04c439b3c9014c1c94f1c882e45c25e92023-12-03T15:14:44ZengMDPI AGJournal of Marine Science and Engineering2077-13122022-06-0110788410.3390/jmse10070884Multi-Level Wavelet-Based Network Embedded with Edge Enhancement Information for Underwater Image EnhancementKaichuan Sun0Fei Meng1Yubo Tian2School of Ocean, Jiangsu University of Science and Technology, Zhenjiang 212100, ChinaSchool of Information and Communication Engineering, Guangzhou Maritime University, Guangzhou 510725, ChinaSchool of Information and Communication Engineering, Guangzhou Maritime University, Guangzhou 510725, ChinaAs an image processing method, underwater image enhancement (UIE) plays an important role in the field of underwater resource detection and engineering research. Currently, the convolutional neural network (CNN)- and Transformer-based methods are the mainstream methods for UIE. However, CNNs usually use pooling to expand the receptive field, which may lead to information loss that is not conducive to feature extraction and analysis. At the same time, edge blurring can easily occur in enhanced images obtained by the existing methods. To address this issue, this paper proposes a framework that combines CNN and Transformer, employs the wavelet transform and inverse wavelet transform for encoding and decoding, and progressively embeds the edge information on the raw image in the encoding process. Specifically, first, features of the raw image and its edge detection image are extracted step by step using the convolution module and the residual dense attention module, respectively, to obtain mixed feature maps of different resolutions. Next, the residual structure Swin Transformer group is used to extract global features. Then, the resulting feature map and the encoder’s hybrid feature map are used for high-resolution feature map reconstruction by the decoder. The experimental results show that the proposed method can achieve an excellent effect in edge information protection and visual reconstruction of images. In addition, the effectiveness of each component of the proposed model is verified by ablation experiments.https://www.mdpi.com/2077-1312/10/7/884underwater image enhancementwavelet transformedge detectionTransformer |
| spellingShingle | Kaichuan Sun Fei Meng Yubo Tian Multi-Level Wavelet-Based Network Embedded with Edge Enhancement Information for Underwater Image Enhancement Journal of Marine Science and Engineering underwater image enhancement wavelet transform edge detection Transformer |
| title | Multi-Level Wavelet-Based Network Embedded with Edge Enhancement Information for Underwater Image Enhancement |
| title_full | Multi-Level Wavelet-Based Network Embedded with Edge Enhancement Information for Underwater Image Enhancement |
| title_fullStr | Multi-Level Wavelet-Based Network Embedded with Edge Enhancement Information for Underwater Image Enhancement |
| title_full_unstemmed | Multi-Level Wavelet-Based Network Embedded with Edge Enhancement Information for Underwater Image Enhancement |
| title_short | Multi-Level Wavelet-Based Network Embedded with Edge Enhancement Information for Underwater Image Enhancement |
| title_sort | multi level wavelet based network embedded with edge enhancement information for underwater image enhancement |
| topic | underwater image enhancement wavelet transform edge detection Transformer |
| url | https://www.mdpi.com/2077-1312/10/7/884 |
| work_keys_str_mv | AT kaichuansun multilevelwaveletbasednetworkembeddedwithedgeenhancementinformationforunderwaterimageenhancement AT feimeng multilevelwaveletbasednetworkembeddedwithedgeenhancementinformationforunderwaterimageenhancement AT yubotian multilevelwaveletbasednetworkembeddedwithedgeenhancementinformationforunderwaterimageenhancement |