Accurate recognition of micromorphology images of epoxy coatings for deep-sea environments based on a deep learning super-resolution method
Crack initiation and extension occur in organic coatings during service in deep-sea environments. However, when extracting detailed crack information from SEM images of epoxy mica coatings at different time periods in a simulated deep-sea fluid-hydraulic environment, uninteresting background regions...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Corrosion Communications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667266924000501 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582109457285120 |
|---|---|
| author | JiaQi Pan Furou Liu Jia Feng Fandi Meng Yufan Chen Jianning Chi Zelan Li Jie Li Li Liu |
| author_facet | JiaQi Pan Furou Liu Jia Feng Fandi Meng Yufan Chen Jianning Chi Zelan Li Jie Li Li Liu |
| author_sort | JiaQi Pan |
| collection | DOAJ |
| description | Crack initiation and extension occur in organic coatings during service in deep-sea environments. However, when extracting detailed crack information from SEM images of epoxy mica coatings at different time periods in a simulated deep-sea fluid-hydraulic environment, uninteresting background regions are treated equally, resulting in unnecessary computational redundancy. To address the relatively blurred edges and unclear textures of SEM images, a crack image super-resolution network based on global mixed attention (GMA-net) is proposed for application to SEM images of organic coatings. The recognition results of the images processed with GMA-net were compared with those of the original images and the images processed with bicubic method, respectively. The results show that this method not only refrains from destroying the clarity of the original images but also greatly outperforms bicubic method in terms of precision, recall, mAP50 and mPA50–95, which are improved by approximately 23.1 %, 32.4 %, 36.4 % and 26.7 %, respectively. This method effectively highlights the details and improves the recognition accuracy of the edge texture with the aim of providing a good basis for subsequent recognition and even lifetime prediction studies. |
| format | Article |
| id | doaj-art-966f6c12ddbf450daeeea29dcce12648 |
| institution | Kabale University |
| issn | 2667-2669 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Corrosion Communications |
| spelling | doaj-art-966f6c12ddbf450daeeea29dcce126482025-01-30T05:15:11ZengElsevierCorrosion Communications2667-26692025-09-01191427Accurate recognition of micromorphology images of epoxy coatings for deep-sea environments based on a deep learning super-resolution methodJiaQi Pan0Furou Liu1Jia Feng2Fandi Meng3Yufan Chen4Jianning Chi5Zelan Li6Jie Li7Li Liu8Corrosion and Protection Center, Northeastern University, Shenyang 110819, ChinaCorrosion and Protection Center, Northeastern University, Shenyang 110819, ChinaChangqing Oilfield Branch NO 9 Oil Production Plant, Yinchuan 750006, ChinaCorrosion and Protection Center, Northeastern University, Shenyang 110819, China; Corresponding authors.Corrosion and Protection Center, Northeastern University, Shenyang 110819, China; Luoyang Ship Material Research Institute, Xiamen 361100, ChinaCollege of Information Science and Engineering, Northeastern University, Shenyang 110169, China; Corresponding authors.College of Information Science and Engineering, Northeastern University, Shenyang 110169, ChinaCorrosion and Protection Center, Northeastern University, Shenyang 110819, ChinaCorrosion and Protection Center, Northeastern University, Shenyang 110819, China; Corresponding authors.Crack initiation and extension occur in organic coatings during service in deep-sea environments. However, when extracting detailed crack information from SEM images of epoxy mica coatings at different time periods in a simulated deep-sea fluid-hydraulic environment, uninteresting background regions are treated equally, resulting in unnecessary computational redundancy. To address the relatively blurred edges and unclear textures of SEM images, a crack image super-resolution network based on global mixed attention (GMA-net) is proposed for application to SEM images of organic coatings. The recognition results of the images processed with GMA-net were compared with those of the original images and the images processed with bicubic method, respectively. The results show that this method not only refrains from destroying the clarity of the original images but also greatly outperforms bicubic method in terms of precision, recall, mAP50 and mPA50–95, which are improved by approximately 23.1 %, 32.4 %, 36.4 % and 26.7 %, respectively. This method effectively highlights the details and improves the recognition accuracy of the edge texture with the aim of providing a good basis for subsequent recognition and even lifetime prediction studies.http://www.sciencedirect.com/science/article/pii/S2667266924000501Super-resolutionOrganic coatingImage recognitionDeep-sea environment |
| spellingShingle | JiaQi Pan Furou Liu Jia Feng Fandi Meng Yufan Chen Jianning Chi Zelan Li Jie Li Li Liu Accurate recognition of micromorphology images of epoxy coatings for deep-sea environments based on a deep learning super-resolution method Corrosion Communications Super-resolution Organic coating Image recognition Deep-sea environment |
| title | Accurate recognition of micromorphology images of epoxy coatings for deep-sea environments based on a deep learning super-resolution method |
| title_full | Accurate recognition of micromorphology images of epoxy coatings for deep-sea environments based on a deep learning super-resolution method |
| title_fullStr | Accurate recognition of micromorphology images of epoxy coatings for deep-sea environments based on a deep learning super-resolution method |
| title_full_unstemmed | Accurate recognition of micromorphology images of epoxy coatings for deep-sea environments based on a deep learning super-resolution method |
| title_short | Accurate recognition of micromorphology images of epoxy coatings for deep-sea environments based on a deep learning super-resolution method |
| title_sort | accurate recognition of micromorphology images of epoxy coatings for deep sea environments based on a deep learning super resolution method |
| topic | Super-resolution Organic coating Image recognition Deep-sea environment |
| url | http://www.sciencedirect.com/science/article/pii/S2667266924000501 |
| work_keys_str_mv | AT jiaqipan accuraterecognitionofmicromorphologyimagesofepoxycoatingsfordeepseaenvironmentsbasedonadeeplearningsuperresolutionmethod AT furouliu accuraterecognitionofmicromorphologyimagesofepoxycoatingsfordeepseaenvironmentsbasedonadeeplearningsuperresolutionmethod AT jiafeng accuraterecognitionofmicromorphologyimagesofepoxycoatingsfordeepseaenvironmentsbasedonadeeplearningsuperresolutionmethod AT fandimeng accuraterecognitionofmicromorphologyimagesofepoxycoatingsfordeepseaenvironmentsbasedonadeeplearningsuperresolutionmethod AT yufanchen accuraterecognitionofmicromorphologyimagesofepoxycoatingsfordeepseaenvironmentsbasedonadeeplearningsuperresolutionmethod AT jianningchi accuraterecognitionofmicromorphologyimagesofepoxycoatingsfordeepseaenvironmentsbasedonadeeplearningsuperresolutionmethod AT zelanli accuraterecognitionofmicromorphologyimagesofepoxycoatingsfordeepseaenvironmentsbasedonadeeplearningsuperresolutionmethod AT jieli accuraterecognitionofmicromorphologyimagesofepoxycoatingsfordeepseaenvironmentsbasedonadeeplearningsuperresolutionmethod AT liliu accuraterecognitionofmicromorphologyimagesofepoxycoatingsfordeepseaenvironmentsbasedonadeeplearningsuperresolutionmethod |