Macroscopic aspergillus recognition using YOLO-CSM
Wenjie Zhao, Zhenhua Ma, Huiying Ru, Xinhang Zhang · 2026
Read Macroscopic aspergillus recognition using YOLO-CSM by Wenjie Zhao, Zhenhua Ma, Huiying Ru, Xinhang Zhang (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-0356242.txt.
Description
Wenjie Zhao and three colleagues build an artificial intelligence system that spots Aspergillus mold in sample images, in this 2026 computer vision study. The fungus matters in medicine and food safety, but its tangled shapes, subtle features, rare strains, and partly hidden colonies defeat simple detectors. The team upgraded a current real-time detection framework with three new modules. One fuses complex structural features. One scores matches by shape to cope with blurred or blocked edges. A third adapts to colonies of different sizes.
The resulting model identified Aspergillus with precision above ninety percent and strong recall, while staying compact enough for practical deployment. The authors report that the shape-aware matching and multi-scale attention were key to handling occlusion and strain variety. They present the system as a faster, more reliable alternative to manual microscopic inspection for laboratories and screening programs.
Catalog record
| CREATOR | Wenjie Zhao, Zhenhua Ma, Huiying Ru, Xinhang Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 39145 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |