An Overview of Image Generation of Industrial Surface Defects
Intelligent defect detection technology combined with deep learning has gained widespread attention in recent years. However, the small number, and diverse and random nature, of defects on industrial surfaces pose a significant challenge to deep learning-based methods. Generating defect images can e...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/19/8160 |
| _version_ | 1797575175140540416 |
|---|---|
| author | Xiaopin Zhong Junwei Zhu Weixiang Liu Chongxin Hu Yuanlong Deng Zongze Wu |
| author_facet | Xiaopin Zhong Junwei Zhu Weixiang Liu Chongxin Hu Yuanlong Deng Zongze Wu |
| author_sort | Xiaopin Zhong |
| collection | DOAJ |
| description | Intelligent defect detection technology combined with deep learning has gained widespread attention in recent years. However, the small number, and diverse and random nature, of defects on industrial surfaces pose a significant challenge to deep learning-based methods. Generating defect images can effectively solve this problem. This paper investigates and summarises traditional defect generation and deep learning-based methods. It analyses the various advantages and disadvantages of these methods and establishes a benchmark through classical adversarial networks and diffusion models. The performance of these methods in generating defect images is analysed through various indices. This paper discusses the existing methods, highlights the shortcomings and challenges in the field of defect image generation, and proposes future research directions. Finally, the paper concludes with a summary. |
| first_indexed | 2024-03-10T21:36:04Z |
| format | Article |
| id | doaj.art-af9a6acc61154cd2a2a12f0ad15b9e12 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T21:36:04Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-af9a6acc61154cd2a2a12f0ad15b9e122023-11-19T15:03:36ZengMDPI AGSensors1424-82202023-09-012319816010.3390/s23198160An Overview of Image Generation of Industrial Surface DefectsXiaopin Zhong0Junwei Zhu1Weixiang Liu2Chongxin Hu3Yuanlong Deng4Zongze Wu5College of Mechatronics and Control Engineering, Shenzhen University, Nanhai Ave., Shenzhen 518060, ChinaCollege of Mechatronics and Control Engineering, Shenzhen University, Nanhai Ave., Shenzhen 518060, ChinaCollege of Mechatronics and Control Engineering, Shenzhen University, Nanhai Ave., Shenzhen 518060, ChinaCollege of Mechatronics and Control Engineering, Shenzhen University, Nanhai Ave., Shenzhen 518060, ChinaShenzhen Institute of Technology, Jiangjunmao Road, Shenzhen 518116, ChinaCollege of Mechatronics and Control Engineering, Shenzhen University, Nanhai Ave., Shenzhen 518060, ChinaIntelligent defect detection technology combined with deep learning has gained widespread attention in recent years. However, the small number, and diverse and random nature, of defects on industrial surfaces pose a significant challenge to deep learning-based methods. Generating defect images can effectively solve this problem. This paper investigates and summarises traditional defect generation and deep learning-based methods. It analyses the various advantages and disadvantages of these methods and establishes a benchmark through classical adversarial networks and diffusion models. The performance of these methods in generating defect images is analysed through various indices. This paper discusses the existing methods, highlights the shortcomings and challenges in the field of defect image generation, and proposes future research directions. Finally, the paper concludes with a summary.https://www.mdpi.com/1424-8220/23/19/8160image generationgenerating adversarial networkdiffusion model |
| spellingShingle | Xiaopin Zhong Junwei Zhu Weixiang Liu Chongxin Hu Yuanlong Deng Zongze Wu An Overview of Image Generation of Industrial Surface Defects Sensors image generation generating adversarial network diffusion model |
| title | An Overview of Image Generation of Industrial Surface Defects |
| title_full | An Overview of Image Generation of Industrial Surface Defects |
| title_fullStr | An Overview of Image Generation of Industrial Surface Defects |
| title_full_unstemmed | An Overview of Image Generation of Industrial Surface Defects |
| title_short | An Overview of Image Generation of Industrial Surface Defects |
| title_sort | overview of image generation of industrial surface defects |
| topic | image generation generating adversarial network diffusion model |
| url | https://www.mdpi.com/1424-8220/23/19/8160 |
| work_keys_str_mv | AT xiaopinzhong anoverviewofimagegenerationofindustrialsurfacedefects AT junweizhu anoverviewofimagegenerationofindustrialsurfacedefects AT weixiangliu anoverviewofimagegenerationofindustrialsurfacedefects AT chongxinhu anoverviewofimagegenerationofindustrialsurfacedefects AT yuanlongdeng anoverviewofimagegenerationofindustrialsurfacedefects AT zongzewu anoverviewofimagegenerationofindustrialsurfacedefects AT xiaopinzhong overviewofimagegenerationofindustrialsurfacedefects AT junweizhu overviewofimagegenerationofindustrialsurfacedefects AT weixiangliu overviewofimagegenerationofindustrialsurfacedefects AT chongxinhu overviewofimagegenerationofindustrialsurfacedefects AT yuanlongdeng overviewofimagegenerationofindustrialsurfacedefects AT zongzewu overviewofimagegenerationofindustrialsurfacedefects |