A One-Stage Approach for Surface Anomaly Detection with Background Suppression Strategies
We explore a one-stage method for surface anomaly detection in industrial scenarios. On one side, encoder-decoder segmentation network is constructed to capture small targets as much as possible, and then dual background suppression mechanisms are designed to reduce noise patterns in coarse and fine...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/7/1829 |
| _version_ | 1811262753190445056 |
|---|---|
| author | Gaokai Liu Ning Yang Lei Guo Shiping Guo Zhi Chen |
| author_facet | Gaokai Liu Ning Yang Lei Guo Shiping Guo Zhi Chen |
| author_sort | Gaokai Liu |
| collection | DOAJ |
| description | We explore a one-stage method for surface anomaly detection in industrial scenarios. On one side, encoder-decoder segmentation network is constructed to capture small targets as much as possible, and then dual background suppression mechanisms are designed to reduce noise patterns in coarse and fine manners. On the other hand, a classification module without learning parameters is built to reduce information loss in small targets due to the inexistence of successive down-sampling processes. Experimental results demonstrate that our one-stage detector achieves state-of-the-art performance in terms of precision, recall and f-score. |
| first_indexed | 2024-04-12T19:32:22Z |
| format | Article |
| id | doaj.art-d66f44315900455d8978ff3076314125 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-12T19:32:22Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d66f44315900455d8978ff30763141252022-12-22T03:19:19ZengMDPI AGSensors1424-82202020-03-01207182910.3390/s20071829s20071829A One-Stage Approach for Surface Anomaly Detection with Background Suppression StrategiesGaokai Liu0Ning Yang1Lei Guo2Shiping Guo3Zhi Chen4School of Automation, Northwestern Polytechnical University, Xi’an 710129, ChinaSchool of Automation, Northwestern Polytechnical University, Xi’an 710129, ChinaSchool of Automation, Northwestern Polytechnical University, Xi’an 710129, ChinaSchool of Automation, Northwestern Polytechnical University, Xi’an 710129, ChinaSchool of Automation, Northwestern Polytechnical University, Xi’an 710129, ChinaWe explore a one-stage method for surface anomaly detection in industrial scenarios. On one side, encoder-decoder segmentation network is constructed to capture small targets as much as possible, and then dual background suppression mechanisms are designed to reduce noise patterns in coarse and fine manners. On the other hand, a classification module without learning parameters is built to reduce information loss in small targets due to the inexistence of successive down-sampling processes. Experimental results demonstrate that our one-stage detector achieves state-of-the-art performance in terms of precision, recall and f-score.https://www.mdpi.com/1424-8220/20/7/1829surface anomaly detectioncomputer visiondeep learningone stagebackground suppression |
| spellingShingle | Gaokai Liu Ning Yang Lei Guo Shiping Guo Zhi Chen A One-Stage Approach for Surface Anomaly Detection with Background Suppression Strategies Sensors surface anomaly detection computer vision deep learning one stage background suppression |
| title | A One-Stage Approach for Surface Anomaly Detection with Background Suppression Strategies |
| title_full | A One-Stage Approach for Surface Anomaly Detection with Background Suppression Strategies |
| title_fullStr | A One-Stage Approach for Surface Anomaly Detection with Background Suppression Strategies |
| title_full_unstemmed | A One-Stage Approach for Surface Anomaly Detection with Background Suppression Strategies |
| title_short | A One-Stage Approach for Surface Anomaly Detection with Background Suppression Strategies |
| title_sort | one stage approach for surface anomaly detection with background suppression strategies |
| topic | surface anomaly detection computer vision deep learning one stage background suppression |
| url | https://www.mdpi.com/1424-8220/20/7/1829 |
| work_keys_str_mv | AT gaokailiu aonestageapproachforsurfaceanomalydetectionwithbackgroundsuppressionstrategies AT ningyang aonestageapproachforsurfaceanomalydetectionwithbackgroundsuppressionstrategies AT leiguo aonestageapproachforsurfaceanomalydetectionwithbackgroundsuppressionstrategies AT shipingguo aonestageapproachforsurfaceanomalydetectionwithbackgroundsuppressionstrategies AT zhichen aonestageapproachforsurfaceanomalydetectionwithbackgroundsuppressionstrategies AT gaokailiu onestageapproachforsurfaceanomalydetectionwithbackgroundsuppressionstrategies AT ningyang onestageapproachforsurfaceanomalydetectionwithbackgroundsuppressionstrategies AT leiguo onestageapproachforsurfaceanomalydetectionwithbackgroundsuppressionstrategies AT shipingguo onestageapproachforsurfaceanomalydetectionwithbackgroundsuppressionstrategies AT zhichen onestageapproachforsurfaceanomalydetectionwithbackgroundsuppressionstrategies |