PCB defect detection based on pseudo-inverse transformation and YOLOv5
Xiaoli Wang, Siti Sarah Maidin, Malathy Batumalay, Azim Uddin, Azim Uddin, Azim Uddin · 2024
Read PCB defect detection based on pseudo-inverse transformation and YOLOv5 by Xiaoli Wang, Siti Sarah Maidin, Malathy Batumalay, Azim Uddin, Azim Uddin, Azim Uddin (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11637289.txt.
Description
Xiaoli Wang and co-authors sped up flaw hunting on circuit boards in a 2024 paper. Board layouts have grown dense, and old check methods miss the fine flaws that scrap a board. Their fix pairs an image clean up model with a tuned version of a known spotter network, YOLOv5, sharpened by a transformer block and loss tweaks.
The clean up model restored flaw photos faster than past tools by a wide span. On their own board set, the spotter caught six flaw kinds at near ninety nine percent accuracy on average. Recall and accuracy beat rival models by more than a tenth each. The authors say the pair suits factory lines that must check boards at speed.
Catalog record
| CREATOR | Xiaoli Wang, Siti Sarah Maidin, Malathy Batumalay, Azim Uddin, Azim Uddin, Azim Uddin |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |