Adaptable physics-based super-resolution for electron backscatter diffraction maps
Abstract In computer vision, single-image super-resolution (SISR) has been extensively explored using convolutional neural networks (CNNs) on optical images, but images outside this domain, such as those from scientific experiments, are not well investigated. Experimental data is often gathered usin...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-12-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-022-00924-2 |
| _version_ | 1811291966189600768 |
|---|---|
| author | Devendra K. Jangid Neal R. Brodnik Michael G. Goebel Amil Khan SaiSidharth Majeti McLean P. Echlin Samantha H. Daly Tresa M. Pollock B. S. Manjunath |
| author_facet | Devendra K. Jangid Neal R. Brodnik Michael G. Goebel Amil Khan SaiSidharth Majeti McLean P. Echlin Samantha H. Daly Tresa M. Pollock B. S. Manjunath |
| author_sort | Devendra K. Jangid |
| collection | DOAJ |
| description | Abstract In computer vision, single-image super-resolution (SISR) has been extensively explored using convolutional neural networks (CNNs) on optical images, but images outside this domain, such as those from scientific experiments, are not well investigated. Experimental data is often gathered using non-optical methods, which alters the metrics for image quality. One such example is electron backscatter diffraction (EBSD), a materials characterization technique that maps crystal arrangement in solid materials, which provides insight into processing, structure, and property relationships. We present a broadly adaptable approach for applying state-of-art SISR networks to generate super-resolved EBSD orientation maps. This approach includes quaternion-based orientation recognition, loss functions that consider rotational effects and crystallographic symmetry, and an inference pipeline to convert network output into established visualization formats for EBSD maps. The ability to generate physically accurate, high-resolution EBSD maps with super-resolution enables high-throughput characterization and broadens the capture capabilities for three-dimensional experimental EBSD datasets. |
| first_indexed | 2024-04-13T04:37:17Z |
| format | Article |
| id | doaj.art-ecf6519f6c074c3ba390f9f64c7c7725 |
| institution | Directory Open Access Journal |
| issn | 2057-3960 |
| language | English |
| last_indexed | 2024-04-13T04:37:17Z |
| publishDate | 2022-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj.art-ecf6519f6c074c3ba390f9f64c7c77252022-12-22T03:02:07ZengNature Portfolionpj Computational Materials2057-39602022-12-01811910.1038/s41524-022-00924-2Adaptable physics-based super-resolution for electron backscatter diffraction mapsDevendra K. Jangid0Neal R. Brodnik1Michael G. Goebel2Amil Khan3SaiSidharth Majeti4McLean P. Echlin5Samantha H. Daly6Tresa M. Pollock7B. S. Manjunath8Electrical and Computer Engineering, University California Santa BarbaraMechanical Engineering, University California Santa BarbaraElectrical and Computer Engineering, University California Santa BarbaraElectrical and Computer Engineering, University California Santa BarbaraComputer Science, University California Santa BarbaraMaterials Department, University California Santa BarbaraMechanical Engineering, University California Santa BarbaraMaterials Department, University California Santa BarbaraElectrical and Computer Engineering, University California Santa BarbaraAbstract In computer vision, single-image super-resolution (SISR) has been extensively explored using convolutional neural networks (CNNs) on optical images, but images outside this domain, such as those from scientific experiments, are not well investigated. Experimental data is often gathered using non-optical methods, which alters the metrics for image quality. One such example is electron backscatter diffraction (EBSD), a materials characterization technique that maps crystal arrangement in solid materials, which provides insight into processing, structure, and property relationships. We present a broadly adaptable approach for applying state-of-art SISR networks to generate super-resolved EBSD orientation maps. This approach includes quaternion-based orientation recognition, loss functions that consider rotational effects and crystallographic symmetry, and an inference pipeline to convert network output into established visualization formats for EBSD maps. The ability to generate physically accurate, high-resolution EBSD maps with super-resolution enables high-throughput characterization and broadens the capture capabilities for three-dimensional experimental EBSD datasets.https://doi.org/10.1038/s41524-022-00924-2 |
| spellingShingle | Devendra K. Jangid Neal R. Brodnik Michael G. Goebel Amil Khan SaiSidharth Majeti McLean P. Echlin Samantha H. Daly Tresa M. Pollock B. S. Manjunath Adaptable physics-based super-resolution for electron backscatter diffraction maps npj Computational Materials |
| title | Adaptable physics-based super-resolution for electron backscatter diffraction maps |
| title_full | Adaptable physics-based super-resolution for electron backscatter diffraction maps |
| title_fullStr | Adaptable physics-based super-resolution for electron backscatter diffraction maps |
| title_full_unstemmed | Adaptable physics-based super-resolution for electron backscatter diffraction maps |
| title_short | Adaptable physics-based super-resolution for electron backscatter diffraction maps |
| title_sort | adaptable physics based super resolution for electron backscatter diffraction maps |
| url | https://doi.org/10.1038/s41524-022-00924-2 |
| work_keys_str_mv | AT devendrakjangid adaptablephysicsbasedsuperresolutionforelectronbackscatterdiffractionmaps AT nealrbrodnik adaptablephysicsbasedsuperresolutionforelectronbackscatterdiffractionmaps AT michaelggoebel adaptablephysicsbasedsuperresolutionforelectronbackscatterdiffractionmaps AT amilkhan adaptablephysicsbasedsuperresolutionforelectronbackscatterdiffractionmaps AT saisidharthmajeti adaptablephysicsbasedsuperresolutionforelectronbackscatterdiffractionmaps AT mcleanpechlin adaptablephysicsbasedsuperresolutionforelectronbackscatterdiffractionmaps AT samanthahdaly adaptablephysicsbasedsuperresolutionforelectronbackscatterdiffractionmaps AT tresampollock adaptablephysicsbasedsuperresolutionforelectronbackscatterdiffractionmaps AT bsmanjunath adaptablephysicsbasedsuperresolutionforelectronbackscatterdiffractionmaps |