A Self-Supervised Model Based on CutPaste-Mix for Ductile Cast Iron Pipe Surface Defect Classification
Online surface inspection systems have gradually found applications in industrial settings. However, the manual effort required to sift through a vast amount of data to identify defect images remains costly. This study delves into a self-supervised binary classification algorithm for addressing the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/19/8243 |
| _version_ | 1827722193355669504 |
|---|---|
| author | Hanxin Zhang Qian Sun Ke Xu |
| author_facet | Hanxin Zhang Qian Sun Ke Xu |
| author_sort | Hanxin Zhang |
| collection | DOAJ |
| description | Online surface inspection systems have gradually found applications in industrial settings. However, the manual effort required to sift through a vast amount of data to identify defect images remains costly. This study delves into a self-supervised binary classification algorithm for addressing the task of defect image classification within ductile cast iron pipe (DCIP) images. Leveraging the CutPaste-Mix data augmentation strategy, we combine defect-free data with enhanced data to input into a deep convolutional neural network. Through Gaussian Density Estimation, we compute anomaly scores to achieve the classification of abnormal regions. Our approach has been implemented in real-world scenarios, involving equipment installation, data collection, and experimentation. The results demonstrate the robust performance of our method, in both the DCIP image dataset and practical field application, achieving an impressive 99.5 AUC (Area Under Curve). This presents a cost-effective means of providing data support for subsequent DCIP surface inspection model training. |
| first_indexed | 2024-03-10T21:34:22Z |
| format | Article |
| id | doaj.art-4c72302d89eb43159af14c7819009908 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T21:34:22Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4c72302d89eb43159af14c78190099082023-11-19T15:04:47ZengMDPI AGSensors1424-82202023-10-012319824310.3390/s23198243A Self-Supervised Model Based on CutPaste-Mix for Ductile Cast Iron Pipe Surface Defect ClassificationHanxin Zhang0Qian Sun1Ke Xu2Collaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing 100083, ChinaCollaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing 100083, ChinaCollaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing 100083, ChinaOnline surface inspection systems have gradually found applications in industrial settings. However, the manual effort required to sift through a vast amount of data to identify defect images remains costly. This study delves into a self-supervised binary classification algorithm for addressing the task of defect image classification within ductile cast iron pipe (DCIP) images. Leveraging the CutPaste-Mix data augmentation strategy, we combine defect-free data with enhanced data to input into a deep convolutional neural network. Through Gaussian Density Estimation, we compute anomaly scores to achieve the classification of abnormal regions. Our approach has been implemented in real-world scenarios, involving equipment installation, data collection, and experimentation. The results demonstrate the robust performance of our method, in both the DCIP image dataset and practical field application, achieving an impressive 99.5 AUC (Area Under Curve). This presents a cost-effective means of providing data support for subsequent DCIP surface inspection model training.https://www.mdpi.com/1424-8220/23/19/8243ductile cast iron pipedefect classificationself-supervisedCutPaste-Mix |
| spellingShingle | Hanxin Zhang Qian Sun Ke Xu A Self-Supervised Model Based on CutPaste-Mix for Ductile Cast Iron Pipe Surface Defect Classification Sensors ductile cast iron pipe defect classification self-supervised CutPaste-Mix |
| title | A Self-Supervised Model Based on CutPaste-Mix for Ductile Cast Iron Pipe Surface Defect Classification |
| title_full | A Self-Supervised Model Based on CutPaste-Mix for Ductile Cast Iron Pipe Surface Defect Classification |
| title_fullStr | A Self-Supervised Model Based on CutPaste-Mix for Ductile Cast Iron Pipe Surface Defect Classification |
| title_full_unstemmed | A Self-Supervised Model Based on CutPaste-Mix for Ductile Cast Iron Pipe Surface Defect Classification |
| title_short | A Self-Supervised Model Based on CutPaste-Mix for Ductile Cast Iron Pipe Surface Defect Classification |
| title_sort | self supervised model based on cutpaste mix for ductile cast iron pipe surface defect classification |
| topic | ductile cast iron pipe defect classification self-supervised CutPaste-Mix |
| url | https://www.mdpi.com/1424-8220/23/19/8243 |
| work_keys_str_mv | AT hanxinzhang aselfsupervisedmodelbasedoncutpastemixforductilecastironpipesurfacedefectclassification AT qiansun aselfsupervisedmodelbasedoncutpastemixforductilecastironpipesurfacedefectclassification AT kexu aselfsupervisedmodelbasedoncutpastemixforductilecastironpipesurfacedefectclassification AT hanxinzhang selfsupervisedmodelbasedoncutpastemixforductilecastironpipesurfacedefectclassification AT qiansun selfsupervisedmodelbasedoncutpastemixforductilecastironpipesurfacedefectclassification AT kexu selfsupervisedmodelbasedoncutpastemixforductilecastironpipesurfacedefectclassification |