Deep Learning-Based Intelligent Sorting of Potato Tubers and Mineral Impurities: System Development and Experimental Evaluation
Qian Wang, Ke Chen, Qiying Li, Qiuying Xu, Weigang Deng · 2026
Read Deep Learning-Based Intelligent Sorting of Potato Tubers and Mineral Impurities: System Development and Experimental Evaluation by Qian Wang, Ke Chen, Qiying Li, Qiuying Xu, Weigang Deng (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-13298011.txt.
Description
Qian Wang and colleagues built a 2026 machine-vision system that sorts harvested potatoes from soil clods and stones. Their detector adapts YOLOv10n with an added attention module and a dynamic blur strategy for training. A programmable controller and pneumatic actuators remove flagged items while the belt runs.
Comparisons with other lightweight models and orthogonal tests weighed belt speed, spacing between items, and the classification threshold. Belt speed mattered most, followed by spacing and then threshold. Under the best combination found, overall sorting accuracy and impurity removal were both high, while few good tubers were rejected by mistake. The results support stable automatic sorting under postharvest conditions.
Catalog record
| CREATOR | Qian Wang, Ke Chen, Qiying Li, Qiuying Xu, Weigang Deng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |