Automated Individual-Level ROI-to-Spectrum Extraction for Hyperspectral Analysis in Forensic Entomology
Yang Xia, Hai Wu, Hao Wang, Guojing Xu, Changbo Chen, Fuxin Song, Yihong Qu, Xiangyan Zhang · 2026
Read Automated Individual-Level ROI-to-Spectrum Extraction for Hyperspectral Analysis in Forensic Entomology by Yang Xia, Hai Wu, Hao Wang, Guojing Xu, Changbo Chen, Fuxin Song, Yihong Qu, Xiangyan 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/PMC13513734.txt.
Description
Yang Xia and seven co-authors automate the slowest step of hyperspectral insect analysis for forensic work, in 2026 work. Hyperspectral cameras record an image plus a full light spectrum per point, which can reveal an insect's age and species, clues to time of death. Analysts usually draw regions of interest by hand before pulling spectra, a slow habit that resists standard practice.
The new workflow segments insect bodies on its own and extracts one spectrum per individual. Tested on larvae, pupae, and adults of forensically important species, it matched every individual in the independent test set against hand annotations. Spectra from the automatic regions closely matched those from manual ones. The authors say the pipeline cuts manual labor and makes insect spectral work easier to repeat across labs, a base for court-facing methods that must be standardized.
Catalog record
| CREATOR | Yang Xia, Hai Wu, Hao Wang, Guojing Xu, Changbo Chen, Fuxin Song, Yihong Qu, Xiangyan Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43500 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |