A Segmentation-driven Editing Method for Bolt Defect Augmentation and Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiao, Yangjie, Zhang, Ke, Wang, Jiacun, Sheng, Xin, Guo, Yurong, Chen, Meijuan, Ren, Zehua, Zheng, Zhaoye, Zhao, Zhenbing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908780270190592
author Xiao, Yangjie
Zhang, Ke
Wang, Jiacun
Sheng, Xin
Guo, Yurong
Chen, Meijuan
Ren, Zehua
Zheng, Zhaoye
Zhao, Zhenbing
author_facet Xiao, Yangjie
Zhang, Ke
Wang, Jiacun
Sheng, Xin
Guo, Yurong
Chen, Meijuan
Ren, Zehua
Zheng, Zhaoye
Zhao, Zhenbing
contents Bolt defect detection is critical to ensure the safety of transmission lines. However, the scarcity of defect images and imbalanced data distributions significantly limit detection performance. To address this problem, we propose a segmentationdriven bolt defect editing method (SBDE) to augment the dataset. First, a bolt attribute segmentation model (Bolt-SAM) is proposed, which enhances the segmentation of complex bolt attributes through the CLAHE-FFT Adapter (CFA) and Multipart- Aware Mask Decoder (MAMD), generating high-quality masks for subsequent editing tasks. Second, a mask optimization module (MOD) is designed and integrated with the image inpainting model (LaMa) to construct the bolt defect attribute editing model (MOD-LaMa), which converts normal bolts into defective ones through attribute editing. Finally, an editing recovery augmentation (ERA) strategy is proposed to recover and put the edited defect bolts back into the original inspection scenes and expand the defect detection dataset. We constructed multiple bolt datasets and conducted extensive experiments. Experimental results demonstrate that the bolt defect images generated by SBDE significantly outperform state-of-the-art image editing models, and effectively improve the performance of bolt defect detection, which fully verifies the effectiveness and application potential of the proposed method. The code of the project is available at https://github.com/Jay-xyj/SBDE.
format Preprint
id arxiv_https___arxiv_org_abs_2508_10509
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Segmentation-driven Editing Method for Bolt Defect Augmentation and Detection
Xiao, Yangjie
Zhang, Ke
Wang, Jiacun
Sheng, Xin
Guo, Yurong
Chen, Meijuan
Ren, Zehua
Zheng, Zhaoye
Zhao, Zhenbing
Computer Vision and Pattern Recognition
Bolt defect detection is critical to ensure the safety of transmission lines. However, the scarcity of defect images and imbalanced data distributions significantly limit detection performance. To address this problem, we propose a segmentationdriven bolt defect editing method (SBDE) to augment the dataset. First, a bolt attribute segmentation model (Bolt-SAM) is proposed, which enhances the segmentation of complex bolt attributes through the CLAHE-FFT Adapter (CFA) and Multipart- Aware Mask Decoder (MAMD), generating high-quality masks for subsequent editing tasks. Second, a mask optimization module (MOD) is designed and integrated with the image inpainting model (LaMa) to construct the bolt defect attribute editing model (MOD-LaMa), which converts normal bolts into defective ones through attribute editing. Finally, an editing recovery augmentation (ERA) strategy is proposed to recover and put the edited defect bolts back into the original inspection scenes and expand the defect detection dataset. We constructed multiple bolt datasets and conducted extensive experiments. Experimental results demonstrate that the bolt defect images generated by SBDE significantly outperform state-of-the-art image editing models, and effectively improve the performance of bolt defect detection, which fully verifies the effectiveness and application potential of the proposed method. The code of the project is available at https://github.com/Jay-xyj/SBDE.
title A Segmentation-driven Editing Method for Bolt Defect Augmentation and Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.10509