Applying a Deep-Learning-Based Keypoint Detection in Analyzing Surface Nanostructures
Scanning tunneling microscopy (STM) imaging has been routinely applied in studying surface nanostructures owing to its capability of acquiring high-resolution molecule-level images of surface nanostructures. However, the image analysis still heavily relies on manual analysis, which is often laboriou...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Molecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1420-3049/28/14/5387 |
| _version_ | 1827732217389907968 |
|---|---|
| author | Shaoxuan Yuan Zhiwen Zhu Jiayi Lu Fengru Zheng Hao Jiang Qiang Sun |
| author_facet | Shaoxuan Yuan Zhiwen Zhu Jiayi Lu Fengru Zheng Hao Jiang Qiang Sun |
| author_sort | Shaoxuan Yuan |
| collection | DOAJ |
| description | Scanning tunneling microscopy (STM) imaging has been routinely applied in studying surface nanostructures owing to its capability of acquiring high-resolution molecule-level images of surface nanostructures. However, the image analysis still heavily relies on manual analysis, which is often laborious and lacks uniform criteria. Recently, machine learning has emerged as a powerful tool in material science research for the automatic analysis and processing of image data. In this paper, we propose a method for analyzing molecular STM images using computer vision techniques. We develop a lightweight deep learning framework based on the YOLO algorithm by labeling molecules with its keypoints. Our framework achieves high efficiency while maintaining accuracy, enabling the recognitions of molecules and further statistical analysis. In addition, the usefulness of this model is exemplified by exploring the length of polyphenylene chains fabricated from on-surface synthesis. We foresee that computer vision methods will be frequently used in analyzing image data in the field of surface chemistry. |
| first_indexed | 2024-03-11T00:46:33Z |
| format | Article |
| id | doaj.art-045a039da02c420ea75e24a798d7b930 |
| institution | Directory Open Access Journal |
| issn | 1420-3049 |
| language | English |
| last_indexed | 2024-03-11T00:46:33Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Molecules |
| spelling | doaj.art-045a039da02c420ea75e24a798d7b9302023-11-18T20:41:21ZengMDPI AGMolecules1420-30492023-07-012814538710.3390/molecules28145387Applying a Deep-Learning-Based Keypoint Detection in Analyzing Surface NanostructuresShaoxuan Yuan0Zhiwen Zhu1Jiayi Lu2Fengru Zheng3Hao Jiang4Qiang Sun5Materials Genome Institute, Shanghai University, Shanghai 200444, ChinaMaterials Genome Institute, Shanghai University, Shanghai 200444, ChinaMaterials Genome Institute, Shanghai University, Shanghai 200444, ChinaMaterials Genome Institute, Shanghai University, Shanghai 200444, ChinaMaterials Genome Institute, Shanghai University, Shanghai 200444, ChinaMaterials Genome Institute, Shanghai University, Shanghai 200444, ChinaScanning tunneling microscopy (STM) imaging has been routinely applied in studying surface nanostructures owing to its capability of acquiring high-resolution molecule-level images of surface nanostructures. However, the image analysis still heavily relies on manual analysis, which is often laborious and lacks uniform criteria. Recently, machine learning has emerged as a powerful tool in material science research for the automatic analysis and processing of image data. In this paper, we propose a method for analyzing molecular STM images using computer vision techniques. We develop a lightweight deep learning framework based on the YOLO algorithm by labeling molecules with its keypoints. Our framework achieves high efficiency while maintaining accuracy, enabling the recognitions of molecules and further statistical analysis. In addition, the usefulness of this model is exemplified by exploring the length of polyphenylene chains fabricated from on-surface synthesis. We foresee that computer vision methods will be frequently used in analyzing image data in the field of surface chemistry.https://www.mdpi.com/1420-3049/28/14/5387YOLOkeypoint recognitioncomputer visionscanning tunneling microscope |
| spellingShingle | Shaoxuan Yuan Zhiwen Zhu Jiayi Lu Fengru Zheng Hao Jiang Qiang Sun Applying a Deep-Learning-Based Keypoint Detection in Analyzing Surface Nanostructures Molecules YOLO keypoint recognition computer vision scanning tunneling microscope |
| title | Applying a Deep-Learning-Based Keypoint Detection in Analyzing Surface Nanostructures |
| title_full | Applying a Deep-Learning-Based Keypoint Detection in Analyzing Surface Nanostructures |
| title_fullStr | Applying a Deep-Learning-Based Keypoint Detection in Analyzing Surface Nanostructures |
| title_full_unstemmed | Applying a Deep-Learning-Based Keypoint Detection in Analyzing Surface Nanostructures |
| title_short | Applying a Deep-Learning-Based Keypoint Detection in Analyzing Surface Nanostructures |
| title_sort | applying a deep learning based keypoint detection in analyzing surface nanostructures |
| topic | YOLO keypoint recognition computer vision scanning tunneling microscope |
| url | https://www.mdpi.com/1420-3049/28/14/5387 |
| work_keys_str_mv | AT shaoxuanyuan applyingadeeplearningbasedkeypointdetectioninanalyzingsurfacenanostructures AT zhiwenzhu applyingadeeplearningbasedkeypointdetectioninanalyzingsurfacenanostructures AT jiayilu applyingadeeplearningbasedkeypointdetectioninanalyzingsurfacenanostructures AT fengruzheng applyingadeeplearningbasedkeypointdetectioninanalyzingsurfacenanostructures AT haojiang applyingadeeplearningbasedkeypointdetectioninanalyzingsurfacenanostructures AT qiangsun applyingadeeplearningbasedkeypointdetectioninanalyzingsurfacenanostructures |