Dual-Level Probability Consistency FS-PFCE for Robust Transfer Classification of Rice Seed Vigor Using Near-Infrared Hyperspectral Imaging
Xiaoping Wu, Yushuo Wang, Jianhao He, Yang Wang, Huan Liang, Liangquan Jia, Shenghui Wang · 2026
Read Dual-Level Probability Consistency FS-PFCE for Robust Transfer Classification of Rice Seed Vigor Using Near-Infrared Hyperspectral Imaging by Xiaoping Wu, Yushuo Wang, Jianhao He, Yang Wang, Huan Liang, Liangquan Jia, Shenghui 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-13610310.txt.
Description
Xiaoping Wu and co-authors wrote a study from 2026 on grading rice seed strength with a special camera. Seed strength, called vigor, tells how well a seed will sprout and grow. The camera reads light past the red end of the spectrum, which can show the seed's state without harming it. The snag is that each rice type reflects light in its own way, so a model trained on one type often fails on the next.
The team built a method that trains on one main type and then adapts to new types with few samples. They used nine hundred seeds from three types in all. Their method sorted seeds of the new types far more truly than a direct transfer of the old model. It also stayed steady when the main-type share changed. The team sees it as a tool for seed checks that do no harm.
Catalog record
| CREATOR | Xiaoping Wu, Yushuo Wang, Jianhao He, Yang Wang, Huan Liang, Liangquan Jia, Shenghui Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 67 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |