Residual neural network-based fully convolutional network for microstructure segmentation
- Title
- Residual neural network-based fully convolutional network for microstructure segmentation
- Author
- 이승환
- Keywords
- Submerged arc welding; carbon steel; acicular ferrite; fraction; segmentation; deep learning; fully convolutional network; ResNet
- Issue Date
- 2019-11
- Publisher
- TAYLOR & FRANCIS LTD
- Citation
- SCIENCE AND TECHNOLOGY OF WELDING AND JOINING, v. 25, no. 4, Page. 282-289
- Abstract
- In this study, microstructures of weldment produced using carbon steel A516 grade 60 were analysed via a deep learning approach to measure the fraction of acicular ferrite which considerably influences on mechanical properties of carbon steel. The fully convolutional network was used to conduct the image segmentation. Submerged arc welding was used for welding, and the dataset was constructed using optical microscope. The model was compiled with ResNet, which is the state-of-the-art classifier used as an encoder. The model is trained to distinguish acicular ferrite from microstructures of dataset images and then estimate its accuracy. As a result, the mean intersection over union, which is a metric commonly used to evaluate image segmentation, was shown to be higher than 85%.
- URI
- https://www.tandfonline.com/doi/full/10.1080/13621718.2019.1687635https://repository.hanyang.ac.kr/handle/20.500.11754/155363
- ISSN
- 1362-1718; 1743-2936
- DOI
- 10.1080/13621718.2019.1687635
- Appears in Collections:
- COLLEGE OF ENGINEERING[S](공과대학) > MECHANICAL ENGINEERING(기계공학부) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML