U-Net을 이용한 이미지 내 부식 시편 분할에 관한 연구
Study on Segmentation of Corroded Specimens in Images Using U-Net
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study proposes an image segmentation technique utilizing the U-Net model to effectively segment the cross-sections of corroded specimens. The proposed model, leveraging an encoder-decoder architecture with skip connections, enables high-resolution segmentation, which is advantageous for the precise delineation of complex corroded areas. After training the model on a labeled image dataset, performance evaluation using test images demonstrated that the proposed U-Net model achieved high accuracy and IoU scores, thereby confirming its excellent performance. These results indicate that machine learning-based long-term image analysis can contribute to the efficient and straightforward segmentation of specimens.
Abstract
This study proposes an image segmentation technique utilizing the U-Net model to effectively segment the cross-sections of corroded specimens. The proposed model, leveraging an encoder-decoder architecture with skip connections, enables high-resolution segmentation, which is advantageous for the precise delineation of complex corroded areas. After training the model on a labeled image dataset, performance evaluation using test images demonstrated that the proposed U-Net model achieved high accuracy and IoU scores, thereby confirming its excellent performance. These results indicate that machine learning-based long-term image analysis can contribute to the efficient and straightforward segmentation of specimens.
참고문헌 (17)
- J. Guo, "Efficient metal corrosion area detection model combining convolution and transformer", Applied Sciences, 14, pp.9900~ (2024)
- B. Kim, "Trends in image processing techniques applied to corrosion detection and analysis", Journal of Surface Science and Engineering, 56, pp.353~370 (2023)
- Y. Shi, "Corrosion-resistant high-entropy alloys : A review", Metals, 7, pp.43~ (2017)
- M. M. H. Imran, "Application of artificial intelligence in marine corrosion prediction and detection", Journal of Marine Science and Engineering, 11, pp.256~ (2023)
- Y. Yu, "Techniques and challenges of image segmentation: A review", Electronics, 12, pp.1199~ (2023)
- N. N. A. Ortega, "Corrosion analysis through an adaptive preprocessing strategy using the K-means algorithm", Procedia Computer Science, 219, pp.586~595 (2023)
- J. Shen, "Real-time superpixel segmentation by DBSCAN clustering algorithm", IEEE Transactions on Image Processing, 25, pp.5933~5942 (2016)
- C. Rother, ""GrabCut" interactive foreground extraction using iterated graph cuts", ACM Transactions on Graphics(TOG), 23, pp.309~314 (2004)
- Y. Mo, "Review the state-of-the-art technologies of semantic segmentation based on deep learning", Neurocomputing, 493, pp.626~646 (2022)
- Y. LeCun, "Deep learning", Nature, 521, pp.436~444 (2015)
- Z. Li, "A survey of convolutional neural networks: Analysis, applications, and prospects", IEEE Transactions on Neural Networks and Learning Systems, 33, pp.6999~7019 (2021)
- O. Ronneberger, "U-Net:Convolutional networks for biomedical image segmentation", International Conference on Medical Image Computing and Computer-Assisted Intervention, 9351, pp.234~241 (2015)
- Z. Huang, "Trans-DCN: A high-efficiency and adaptive deep network for bridge cable surface defect segmentation", Remote Sensing, 16, pp.2711~ (2024)
- X. Ding, "CFF-Net : Cross-hierarchy feature fusion network based on composite dual-channel encoder for surface defect segmentation", Electronics, 13, pp.4714~ (2024)
- E. M. Rey, "Human-in-the-loop machine learning:A state of the art", Artificial Intelligence Review, 56, pp.3005~3054 (2023)
- L. Liu, "A survey on U-shaped networks in medical image segmentation", Neurocomputing, 409, pp.244~258 (2020)