Chrysoprase color grading with machine learning: A systematic approach
Yuansheng Jiang, Ying Guo, Vien Cheung, Pohsun Wang, Stephen Westland · 2026
Read Chrysoprase color grading with machine learning: A systematic approach by Yuansheng Jiang, Ying Guo, Vien Cheung, Pohsun Wang, Stephen Westland (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-0349205.txt.
Description
Yuansheng Jiang and co-authors built an automatic grader for chrysoprase, a green gemstone whose price depends heavily on colour judged by eye. Human grading varies from person to person, so the team measured colour precisely for fifty-one stones with a light instrument. They generated hundreds of reference greens and taught several computer methods to sort stones into colour groups.
A simple statistical method and a neural network both scored near the top, and the team chose the simpler one because its reasoning is easy to follow and it runs fast. On a fresh set of real stones it sorted every stone correctly within this dataset. The authors offer the framework as a path toward fairer, repeatable grading for a trade built on subjective judgement.
Catalog record
| CREATOR | Yuansheng Jiang, Ying Guo, Vien Cheung, Pohsun Wang, Stephen Westland |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47921 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |