Detection of Frost‐Damaged Maize Kernels for Food Quality Screening Using Hyperspectral Imaging and 2D‐COS‐Assisted Deep Learning
Jiaxuan Nan, Dingguo Wang, Huihui Wang, Changxu Hu, Jiaxuan Li, Wuping Zhang, Fuzhong Li, Jiwan Han · 2026
Read Detection of Frost‐Damaged Maize Kernels for Food Quality Screening Using Hyperspectral Imaging and 2D‐COS‐Assisted Deep Learning by Jiaxuan Nan, Dingguo Wang, Huihui Wang, Changxu Hu, Jiaxuan Li, Wuping Zhang, Fuzhong Li, Jiwan Han (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-13586999.txt.
Description
Jiaxuan Nan and co-authors build a fast screen for frost-damaged maize kernels in a 2026 paper. Freezing harms kernel chemistry and food value, yet standard lab tests destroy samples and run slowly. A supply chain needs quick, gentle checks that can sort grain at scale.
Their method pairs hyperspectral imaging, scanning light beyond the visible range, with deep learning. A two-dimensional correlation step first sharpened the weak spectral signs of frost damage, picking out hundreds of telling bands. The resulting model spotted damaged kernels with accuracy near ninety-seven percent and strong recall, and it held up on fresh samples. The authors present the system as a reliable, non-destructive tool for food quality screening.
Catalog record
| CREATOR | Jiaxuan Nan, Dingguo Wang, Huihui Wang, Changxu Hu, Jiaxuan Li, Wuping Zhang, Fuzhong Li, Jiwan Han |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 64 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |