Autoencoder-Based Unsupervised Surface Defect Detection Using Two-Stage Training
Journal of Imaging · 05.05.2024 · 10 (5) · 111
DOI: 10.3390/jimaging10050111 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 05.05.2024. Verfasst von Tesfaye Getachew Shiferaw und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Southeast University, Nanjing 211189, China. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: This work is supported by the Significant Science And Technology Project of Nanjing, Significant Science And Technology Project of Nanjing.
Abstract (Originalsprache)
Accurately detecting defects while reconstructing a high-quality normal background in surface defect detection using unsupervised methods remains a significant challenge. This study proposes an unsupervised method that effectively addresses this challenge by achieving both accurate defect detection and a high-quality normal background reconstruction without noise. We propose an adaptive weighted structural similarity (AW-SSIM) loss for focused feature learning. AW-SSIM improves structural similarity (SSIM) loss by assigning different weights to its sub-functions of luminance, contrast, and structure based on their relative importance for a specific training sample. Moreover, it dynamically adjusts the Gaussian window’s standard deviation (σ) during loss calculation to balance noise reduction and detail preservation. An artificial defect generation algorithm (ADGA) is proposed to generate an artificial defect closely resembling real ones. We use a two-stage training strategy. In the first stage, the model trains only on normal samples using AW-SSIM loss, allowing it to learn robust representations of normal features. In the second stage of training, the weights obtained from the first stage are used to train the model on both normal and artificially defective training samples. Additionally, the second stage employs a combined learned Perceptual Image Patch Similarity (LPIPS) and AW-SSIM loss. The combined loss helps the model in achieving high-quality normal background reconstruction while maintaining accurate defect detection. Extensive experimental results demonstrate that our proposed method achieves a state-of-the-art defect detection accuracy. The proposed method achieved an average area under the receiver operating characteristic curve (AuROC) of 97.69% on six samples from the MVTec anomaly detection dataset.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science and Engineering, Southeast University, Nanjing 211189, China.
- Key Laboratory of Computer Network and Information Integration, Southeast University, Ministry of Education, Nanjing 211189, China.
ORCID-Profile: Li Yao
Förderung
- This work is supported by the Significant Science And Technology Project of Nanjing
- Significant Science And Technology Project of Nanjing
Zitieren
APA
Getachew Shiferaw, T., & Yao, L. (2024). Autoencoder-Based Unsupervised Surface Defect Detection Using Two-Stage Training. Journal of Imaging, 10(5), 111. https://doi.org/10.3390/jimaging10050111
Vancouver
Getachew Shiferaw T, Yao L. Autoencoder-Based Unsupervised Surface Defect Detection Using Two-Stage Training. Journal of Imaging. 2024;10(5):111. doi:10.3390/jimaging10050111
BibTeX
@article{GetachewShiferaw2024,
author = {Getachew Shiferaw, Tesfaye and Yao, Li},
title = {Autoencoder-Based Unsupervised Surface Defect Detection Using Two-Stage Training},
journal = {Journal of Imaging},
year = {2024},
volume = {10},
number = {5},
pages = {111},
doi = {10.3390/jimaging10050111}
}
EUVIMED