Automated detection of defective coffee beans based on improved YOLOv10 framework
Sunyan Hong, Dengji Zhang, Haiyang Chi, Jun He, Xiudong Guo, Hui Fu, Lu Wang · 2026
Read Automated detection of defective coffee beans based on improved YOLOv10 framework by Sunyan Hong, Dengji Zhang, Haiyang Chi, Jun He, Xiudong Guo, Hui Fu, Lu Wang (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/pmc-13276431.txt.
Description
Sunyan Hong and colleagues present a 2026 vision system for spotting defective green coffee beans automatically. Hand sorting is slow, tiring, and inconsistent, yet bean quality drives prices worldwide. Their system builds on the YOLOv10 detection model and targets fast factory use.
Three design changes cut computing load while sharpening fine detail and wider context. The dataset covered seven defect types graded to speciality coffee standards. Five-fold testing gave detection scores above ninety-eight percent for precision and recall, with answers in about two milliseconds. The model was also smaller and faster than a newer baseline, which suits sorting lines with limited hardware.
Catalog record
| CREATOR | Sunyan Hong, Dengji Zhang, Haiyang Chi, Jun He, Xiudong Guo, Hui Fu, Lu Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 83 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |