Deep-Learning-Based Surface Texture Feature Simulation for Surface Defect Inspection
In this research, a simulation system based on a physical model and its lighting feature is developed to perform three-dimensional model creation, and graphics software is used to randomly generate a simulated surface with defects, which also cooperates with the virtual environment to reproduce the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/14/7/1465 |
| _version_ | 1797415323023966208 |
|---|---|
| author | Chao-Ching Ho Li-Lun Tai Eugene Su |
| author_facet | Chao-Ching Ho Li-Lun Tai Eugene Su |
| author_sort | Chao-Ching Ho |
| collection | DOAJ |
| description | In this research, a simulation system based on a physical model and its lighting feature is developed to perform three-dimensional model creation, and graphics software is used to randomly generate a simulated surface with defects, which also cooperates with the virtual environment to reproduce the original environment. Furthermore, the use of a generative adversarial network to optimize the virtual dataset created symmetrically by the system is studied in order to reduce the effect of the difference between the real and virtual images. This system compensates for the condition of data imbalance occurring between qualified products and defective products in the production line, and a large amount of random data with and without defects can be created. In addition, the process of the database creation is classified and marked, such that complicated and time-consuming preliminary steps can be reduced; therefore, the data collection cost can be significantly reduced and the uncertainly associated with manual operation is also reduced. When a simulated textured surface generated from this system is used to perform training, the inspection background accuracy reaches 98%, and the accuracy also reaches 78% in real defect inspection process; therefore, the location of the defect can be determined completely. |
| first_indexed | 2024-03-09T05:47:03Z |
| format | Article |
| id | doaj.art-55d39bd5a83644989afce25d62d0e839 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-09T05:47:03Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-55d39bd5a83644989afce25d62d0e8392023-12-03T12:20:12ZengMDPI AGSymmetry2073-89942022-07-01147146510.3390/sym14071465Deep-Learning-Based Surface Texture Feature Simulation for Surface Defect InspectionChao-Ching Ho0Li-Lun Tai1Eugene Su2Graduate Institute of Manufacturing Technology, Department of Mechanical Engineering, National Taipei University of Technology, Taipei 106344, TaiwanGraduate Institute of Manufacturing Technology, Department of Mechanical Engineering, National Taipei University of Technology, Taipei 106344, TaiwanGraduate Institute of Manufacturing Technology, Department of Mechanical Engineering, National Taipei University of Technology, Taipei 106344, TaiwanIn this research, a simulation system based on a physical model and its lighting feature is developed to perform three-dimensional model creation, and graphics software is used to randomly generate a simulated surface with defects, which also cooperates with the virtual environment to reproduce the original environment. Furthermore, the use of a generative adversarial network to optimize the virtual dataset created symmetrically by the system is studied in order to reduce the effect of the difference between the real and virtual images. This system compensates for the condition of data imbalance occurring between qualified products and defective products in the production line, and a large amount of random data with and without defects can be created. In addition, the process of the database creation is classified and marked, such that complicated and time-consuming preliminary steps can be reduced; therefore, the data collection cost can be significantly reduced and the uncertainly associated with manual operation is also reduced. When a simulated textured surface generated from this system is used to perform training, the inspection background accuracy reaches 98%, and the accuracy also reaches 78% in real defect inspection process; therefore, the location of the defect can be determined completely.https://www.mdpi.com/2073-8994/14/7/1465automated optical inspectiondeep learningtexture mappingtransfer learning |
| spellingShingle | Chao-Ching Ho Li-Lun Tai Eugene Su Deep-Learning-Based Surface Texture Feature Simulation for Surface Defect Inspection Symmetry automated optical inspection deep learning texture mapping transfer learning |
| title | Deep-Learning-Based Surface Texture Feature Simulation for Surface Defect Inspection |
| title_full | Deep-Learning-Based Surface Texture Feature Simulation for Surface Defect Inspection |
| title_fullStr | Deep-Learning-Based Surface Texture Feature Simulation for Surface Defect Inspection |
| title_full_unstemmed | Deep-Learning-Based Surface Texture Feature Simulation for Surface Defect Inspection |
| title_short | Deep-Learning-Based Surface Texture Feature Simulation for Surface Defect Inspection |
| title_sort | deep learning based surface texture feature simulation for surface defect inspection |
| topic | automated optical inspection deep learning texture mapping transfer learning |
| url | https://www.mdpi.com/2073-8994/14/7/1465 |
| work_keys_str_mv | AT chaochingho deeplearningbasedsurfacetexturefeaturesimulationforsurfacedefectinspection AT liluntai deeplearningbasedsurfacetexturefeaturesimulationforsurfacedefectinspection AT eugenesu deeplearningbasedsurfacetexturefeaturesimulationforsurfacedefectinspection |