Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction
The occurrence of anomalies on the surface of industrial products can lead to issues such as decreased product quality, reduced production efficiency, and safety hazards. Early detection and resolution of these problems are crucial for ensuring the quality and efficiency of production. The key chall...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/1/264 |
| _version_ | 1797358114345844736 |
|---|---|
| author | Tao Peng Yu Zheng Lin Zhao Enrang Zheng |
| author_facet | Tao Peng Yu Zheng Lin Zhao Enrang Zheng |
| author_sort | Tao Peng |
| collection | DOAJ |
| description | The occurrence of anomalies on the surface of industrial products can lead to issues such as decreased product quality, reduced production efficiency, and safety hazards. Early detection and resolution of these problems are crucial for ensuring the quality and efficiency of production. The key challenge in applying deep learning to surface defect detection of industrial products is the scarcity of defect samples, which will make supervised learning methods unsuitable for surface defect detection problems. Therefore, it is a reasonable solution to use anomaly detection methods to deal with surface defect detection. Among image-based anomaly detection, reconstruction-based methods are the most commonly used. However, reconstruction-based approaches lack the involvement of defect samples in the training process, posing the risk of a perfect reconstruction of defects by the reconstruction network. In this paper, we propose a reconstruction-based defect detection algorithm that addresses these challenges by utilizing more realistic synthetic anomalies for training. Our model focuses on creating authentic synthetic defects and introduces an auto-encoder image reconstruction network with deep feature consistency constraints, as well as a defect separation network with a large receptive field. We conducted experiments on the challenging MVTec anomaly detection dataset and our trained model achieved an AUROC score of 99.70% and an average precision (AP) score of 99.87%. Our method surpasses recently proposed defect detection algorithms, thereby enhancing the accuracy of surface defect detection in industrial products. |
| first_indexed | 2024-03-08T14:57:07Z |
| format | Article |
| id | doaj.art-36dbf7e291bf4fb28536c56f543df0b9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T14:57:07Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-36dbf7e291bf4fb28536c56f543df0b92024-01-10T15:09:19ZengMDPI AGSensors1424-82202024-01-0124126410.3390/s24010264Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map PredictionTao Peng0Yu Zheng1Lin Zhao2Enrang Zheng3School of Electrical and Control Engineering, Shaanxi University of Science and Technology, Xi’an 710026, ChinaSchool of Cyber Engineering, Xidian University, Xi’an 710126, ChinaSchool of Electrical and Control Engineering, Shaanxi University of Science and Technology, Xi’an 710026, ChinaSchool of Electrical and Control Engineering, Shaanxi University of Science and Technology, Xi’an 710026, ChinaThe occurrence of anomalies on the surface of industrial products can lead to issues such as decreased product quality, reduced production efficiency, and safety hazards. Early detection and resolution of these problems are crucial for ensuring the quality and efficiency of production. The key challenge in applying deep learning to surface defect detection of industrial products is the scarcity of defect samples, which will make supervised learning methods unsuitable for surface defect detection problems. Therefore, it is a reasonable solution to use anomaly detection methods to deal with surface defect detection. Among image-based anomaly detection, reconstruction-based methods are the most commonly used. However, reconstruction-based approaches lack the involvement of defect samples in the training process, posing the risk of a perfect reconstruction of defects by the reconstruction network. In this paper, we propose a reconstruction-based defect detection algorithm that addresses these challenges by utilizing more realistic synthetic anomalies for training. Our model focuses on creating authentic synthetic defects and introduces an auto-encoder image reconstruction network with deep feature consistency constraints, as well as a defect separation network with a large receptive field. We conducted experiments on the challenging MVTec anomaly detection dataset and our trained model achieved an AUROC score of 99.70% and an average precision (AP) score of 99.87%. Our method surpasses recently proposed defect detection algorithms, thereby enhancing the accuracy of surface defect detection in industrial products.https://www.mdpi.com/1424-8220/24/1/264defect detectionimage reconstructionsynthetic anomaliesdefect separation |
| spellingShingle | Tao Peng Yu Zheng Lin Zhao Enrang Zheng Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction Sensors defect detection image reconstruction synthetic anomalies defect separation |
| title | Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction |
| title_full | Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction |
| title_fullStr | Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction |
| title_full_unstemmed | Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction |
| title_short | Industrial Product Surface Anomaly Detection with Realistic Synthetic Anomalies Based on Defect Map Prediction |
| title_sort | industrial product surface anomaly detection with realistic synthetic anomalies based on defect map prediction |
| topic | defect detection image reconstruction synthetic anomalies defect separation |
| url | https://www.mdpi.com/1424-8220/24/1/264 |
| work_keys_str_mv | AT taopeng industrialproductsurfaceanomalydetectionwithrealisticsyntheticanomaliesbasedondefectmapprediction AT yuzheng industrialproductsurfaceanomalydetectionwithrealisticsyntheticanomaliesbasedondefectmapprediction AT linzhao industrialproductsurfaceanomalydetectionwithrealisticsyntheticanomaliesbasedondefectmapprediction AT enrangzheng industrialproductsurfaceanomalydetectionwithrealisticsyntheticanomaliesbasedondefectmapprediction |