Recovering Microscopic Images in Material Science Documents by Image Inpainting
Microscopic images in material science documents have increased in number due to the growth and common use of electron microscopy instruments. Through the use of data mining techniques, they are easily accessible and can be obtained from documents published online. As data-driven approaches are beco...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/6/4071 |
| _version_ | 1797613545200812032 |
|---|---|
| author | Taeyun Kim Byung Chul Yeo |
| author_facet | Taeyun Kim Byung Chul Yeo |
| author_sort | Taeyun Kim |
| collection | DOAJ |
| description | Microscopic images in material science documents have increased in number due to the growth and common use of electron microscopy instruments. Through the use of data mining techniques, they are easily accessible and can be obtained from documents published online. As data-driven approaches are becoming increasingly common in the material science field, massively acquired experimental images through microscopy play important roles in terms of developing an artificial intelligence (AI) model for the purposes of automatically diagnosing crucial material structures. However, irrelevant objects (e.g., letters, scale bars, and arrows) that are often present inside original microscopic photos should be removed for the purposes of improving the AI models. To avoid the issue above, we applied four image inpainting algorithms (i.e., shift-net, global and local, contextual attention, and gated convolution) to a learning approach, with the aim of recovering microscopic images in journal papers. We estimated the structural similarity index measure (SSIM) and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>ℓ</mi><mn>1</mn></msub></mrow></semantics></math></inline-formula>/<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>ℓ</mi><mn>2</mn></msub></mrow></semantics></math></inline-formula> errors, which are often used as measures of image quality. Lastly, we observed that gated convolution possessed the best performance for inpainting the microscopic images. |
| first_indexed | 2024-03-11T06:57:13Z |
| format | Article |
| id | doaj.art-28a9745b89ac462397e9c2d895ea8549 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T06:57:13Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-28a9745b89ac462397e9c2d895ea85492023-11-17T09:31:05ZengMDPI AGApplied Sciences2076-34172023-03-01136407110.3390/app13064071Recovering Microscopic Images in Material Science Documents by Image InpaintingTaeyun Kim0Byung Chul Yeo1Department of Energy Resources Engineering, Pukyong National University, Busan 48513, Republic of KoreaDepartment of Energy Resources Engineering, Pukyong National University, Busan 48513, Republic of KoreaMicroscopic images in material science documents have increased in number due to the growth and common use of electron microscopy instruments. Through the use of data mining techniques, they are easily accessible and can be obtained from documents published online. As data-driven approaches are becoming increasingly common in the material science field, massively acquired experimental images through microscopy play important roles in terms of developing an artificial intelligence (AI) model for the purposes of automatically diagnosing crucial material structures. However, irrelevant objects (e.g., letters, scale bars, and arrows) that are often present inside original microscopic photos should be removed for the purposes of improving the AI models. To avoid the issue above, we applied four image inpainting algorithms (i.e., shift-net, global and local, contextual attention, and gated convolution) to a learning approach, with the aim of recovering microscopic images in journal papers. We estimated the structural similarity index measure (SSIM) and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>ℓ</mi><mn>1</mn></msub></mrow></semantics></math></inline-formula>/<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>ℓ</mi><mn>2</mn></msub></mrow></semantics></math></inline-formula> errors, which are often used as measures of image quality. Lastly, we observed that gated convolution possessed the best performance for inpainting the microscopic images.https://www.mdpi.com/2076-3417/13/6/4071microscopic imagesmaterial science literatureimage inpainting |
| spellingShingle | Taeyun Kim Byung Chul Yeo Recovering Microscopic Images in Material Science Documents by Image Inpainting Applied Sciences microscopic images material science literature image inpainting |
| title | Recovering Microscopic Images in Material Science Documents by Image Inpainting |
| title_full | Recovering Microscopic Images in Material Science Documents by Image Inpainting |
| title_fullStr | Recovering Microscopic Images in Material Science Documents by Image Inpainting |
| title_full_unstemmed | Recovering Microscopic Images in Material Science Documents by Image Inpainting |
| title_short | Recovering Microscopic Images in Material Science Documents by Image Inpainting |
| title_sort | recovering microscopic images in material science documents by image inpainting |
| topic | microscopic images material science literature image inpainting |
| url | https://www.mdpi.com/2076-3417/13/6/4071 |
| work_keys_str_mv | AT taeyunkim recoveringmicroscopicimagesinmaterialsciencedocumentsbyimageinpainting AT byungchulyeo recoveringmicroscopicimagesinmaterialsciencedocumentsbyimageinpainting |