YOLO-MDEW:Improved YOLOv8 for application of wood board edge banding defect detection
Enjing Xiao, Rougang Zhou, Zhenchao Ruan, Chou Jay Tsai Chien, Junjie Zhu · 2026
Read YOLO-MDEW:Improved YOLOv8 for application of wood board edge banding defect detection by Enjing Xiao, Rougang Zhou, Zhenchao Ruan, Chou Jay Tsai Chien, Junjie Zhu (2026) 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/plos-pone-0348758.txt.
Description
Enjing Xiao and co-workers improve a camera-based defect spotter for the banded edges of wooden furniture panels. Edge banding flaws are small and easy to miss, which costs makers rework and returns. Their 2026 study upgrades a compact detection model with feature blending across scales, a sharper pooling block with attention, and a loss rule that settles faster on the flaw's true box.
On a purpose-built photo set of panel edges, the improved model scored higher on the standard detection measure than the base model it grew from. The authors describe fewer misses and fewer false alarms as the practical payoff. Automated edge checks could steady quality on furniture lines where tired eyes now do the watching.
Catalog record
| CREATOR | Enjing Xiao, Rougang Zhou, Zhenchao Ruan, Chou Jay Tsai Chien, Junjie Zhu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40533 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |