Focusing on Cracks with Instance Normalization Wavelet Layer
Automatic crack detection is challenging, owing to the complex and thin topologies, diversity, and background noises of cracks. Inspired by the wavelet theory, we present an instance normalization wavelet (INW) layer and embed the layer into the deep model for segmentation. The proposed layer employ...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/1/146 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548919907024896 |
|---|---|
| author | Lei Guo Fengguang Xiong Yaming Cao Hongxin Xue Lei Cui Xie Han |
| author_facet | Lei Guo Fengguang Xiong Yaming Cao Hongxin Xue Lei Cui Xie Han |
| author_sort | Lei Guo |
| collection | DOAJ |
| description | Automatic crack detection is challenging, owing to the complex and thin topologies, diversity, and background noises of cracks. Inspired by the wavelet theory, we present an instance normalization wavelet (INW) layer and embed the layer into the deep model for segmentation. The proposed layer employs prior knowledge in the wavelets to capture the crack features and filter the high-frequency noises simultaneously, accelerating the convergence of model training. Furthermore, instance normalization in our layer is utilized to mitigate the feature differences, boosting the generalization capability. In addition, a fusion layer is added to merge the information across the different layers. The comparison experiments and ablation studies demonstrate that the INW layer steadily enhances recognition and convergence performance on the DeepCrack dataset and CRACK500 dataset. |
| format | Article |
| id | doaj-art-58c56f06beab4877bb6e28d0cd92fefe |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-58c56f06beab4877bb6e28d0cd92fefe2025-01-10T13:21:02ZengMDPI AGSensors1424-82202024-12-0125114610.3390/s25010146Focusing on Cracks with Instance Normalization Wavelet LayerLei Guo0Fengguang Xiong1Yaming Cao2Hongxin Xue3Lei Cui4Xie Han5Shanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, ChinaShanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, ChinaShanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, ChinaShanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, ChinaNational Supercomputer Center, Shandong Computer Science Center, Jinan 250013, ChinaShanxi Key Laboratory of Machine Vision and Virtual Reality, North University of China, Taiyuan 030051, ChinaAutomatic crack detection is challenging, owing to the complex and thin topologies, diversity, and background noises of cracks. Inspired by the wavelet theory, we present an instance normalization wavelet (INW) layer and embed the layer into the deep model for segmentation. The proposed layer employs prior knowledge in the wavelets to capture the crack features and filter the high-frequency noises simultaneously, accelerating the convergence of model training. Furthermore, instance normalization in our layer is utilized to mitigate the feature differences, boosting the generalization capability. In addition, a fusion layer is added to merge the information across the different layers. The comparison experiments and ablation studies demonstrate that the INW layer steadily enhances recognition and convergence performance on the DeepCrack dataset and CRACK500 dataset.https://www.mdpi.com/1424-8220/25/1/146crack detectionwaveletconvolution neural networksfeature fusion |
| spellingShingle | Lei Guo Fengguang Xiong Yaming Cao Hongxin Xue Lei Cui Xie Han Focusing on Cracks with Instance Normalization Wavelet Layer Sensors crack detection wavelet convolution neural networks feature fusion |
| title | Focusing on Cracks with Instance Normalization Wavelet Layer |
| title_full | Focusing on Cracks with Instance Normalization Wavelet Layer |
| title_fullStr | Focusing on Cracks with Instance Normalization Wavelet Layer |
| title_full_unstemmed | Focusing on Cracks with Instance Normalization Wavelet Layer |
| title_short | Focusing on Cracks with Instance Normalization Wavelet Layer |
| title_sort | focusing on cracks with instance normalization wavelet layer |
| topic | crack detection wavelet convolution neural networks feature fusion |
| url | https://www.mdpi.com/1424-8220/25/1/146 |
| work_keys_str_mv | AT leiguo focusingoncrackswithinstancenormalizationwaveletlayer AT fengguangxiong focusingoncrackswithinstancenormalizationwaveletlayer AT yamingcao focusingoncrackswithinstancenormalizationwaveletlayer AT hongxinxue focusingoncrackswithinstancenormalizationwaveletlayer AT leicui focusingoncrackswithinstancenormalizationwaveletlayer AT xiehan focusingoncrackswithinstancenormalizationwaveletlayer |