Improved U-Net++ with Patch Split for Micro-Defect Inspection in Silk Screen Printing
The trend of multi-variety production is leading to a change in the product type of silk screen prints produced at short intervals. The types and locations of defects that usually occur in silk screen prints may vary greatly and thus, it is difficult for operators to conduct quality inspections for...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/9/4679 |
| _version_ | 1827673065077604352 |
|---|---|
| author | Byungguan Yoon Homin Lee Jongpil Jeong |
| author_facet | Byungguan Yoon Homin Lee Jongpil Jeong |
| author_sort | Byungguan Yoon |
| collection | DOAJ |
| description | The trend of multi-variety production is leading to a change in the product type of silk screen prints produced at short intervals. The types and locations of defects that usually occur in silk screen prints may vary greatly and thus, it is difficult for operators to conduct quality inspections for minuscule defects. In this paper, an improved U-Net++ is proposed based on patch splits for automated quality inspection of small or tiny defects, hereinafter referred to as ‘fine’ defects. The novelty of the method is that, to better handle defects within an image, patch level inputs are considered instead of using the original image as input. In the existing technique with the original image as input, artificial intelligence (AI) learning is not utilized efficiently, whereas our proposed method learns stably, and the Dice score was 0.728, which is approximately 10% higher than the existing method. The proposed model was applied to an actual silk screen printing process. All of the fine defects in products, such as silk screen prints, could be detected regardless of the product size. In addition, it was shown that quality inspection using the patch-split method-based AI is possible even in situations where there are few prior defective data. |
| first_indexed | 2024-03-10T04:19:43Z |
| format | Article |
| id | doaj.art-28682b103faf4299bda0faed029c7ef0 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:19:43Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-28682b103faf4299bda0faed029c7ef02023-11-23T07:52:23ZengMDPI AGApplied Sciences2076-34172022-05-01129467910.3390/app12094679Improved U-Net++ with Patch Split for Micro-Defect Inspection in Silk Screen PrintingByungguan Yoon0Homin Lee1Jongpil Jeong2Department of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon 16419, KoreaAI Reserach, iShango Corporate, 5, Gasan Digital 1-ro, Geumcheon-gu, Seoul 08594, KoreaDepartment of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon 16419, KoreaThe trend of multi-variety production is leading to a change in the product type of silk screen prints produced at short intervals. The types and locations of defects that usually occur in silk screen prints may vary greatly and thus, it is difficult for operators to conduct quality inspections for minuscule defects. In this paper, an improved U-Net++ is proposed based on patch splits for automated quality inspection of small or tiny defects, hereinafter referred to as ‘fine’ defects. The novelty of the method is that, to better handle defects within an image, patch level inputs are considered instead of using the original image as input. In the existing technique with the original image as input, artificial intelligence (AI) learning is not utilized efficiently, whereas our proposed method learns stably, and the Dice score was 0.728, which is approximately 10% higher than the existing method. The proposed model was applied to an actual silk screen printing process. All of the fine defects in products, such as silk screen prints, could be detected regardless of the product size. In addition, it was shown that quality inspection using the patch-split method-based AI is possible even in situations where there are few prior defective data.https://www.mdpi.com/2076-3417/12/9/4679U-Net++patch splitcomputer visiondeep learningsmart factoryinspection |
| spellingShingle | Byungguan Yoon Homin Lee Jongpil Jeong Improved U-Net++ with Patch Split for Micro-Defect Inspection in Silk Screen Printing Applied Sciences U-Net++ patch split computer vision deep learning smart factory inspection |
| title | Improved U-Net++ with Patch Split for Micro-Defect Inspection in Silk Screen Printing |
| title_full | Improved U-Net++ with Patch Split for Micro-Defect Inspection in Silk Screen Printing |
| title_fullStr | Improved U-Net++ with Patch Split for Micro-Defect Inspection in Silk Screen Printing |
| title_full_unstemmed | Improved U-Net++ with Patch Split for Micro-Defect Inspection in Silk Screen Printing |
| title_short | Improved U-Net++ with Patch Split for Micro-Defect Inspection in Silk Screen Printing |
| title_sort | improved u net with patch split for micro defect inspection in silk screen printing |
| topic | U-Net++ patch split computer vision deep learning smart factory inspection |
| url | https://www.mdpi.com/2076-3417/12/9/4679 |
| work_keys_str_mv | AT byungguanyoon improvedunetwithpatchsplitformicrodefectinspectioninsilkscreenprinting AT hominlee improvedunetwithpatchsplitformicrodefectinspectioninsilkscreenprinting AT jongpiljeong improvedunetwithpatchsplitformicrodefectinspectioninsilkscreenprinting |