Deep learning-driven automatic counting of petal number in cut chrysanthemum inflorescence
Shanpeng Xu, Jingshan Lu, Lian Ding, Fei Zhang, Fadi Chen, Zhenxing Wang, Sumei Chen, Weimin Fang, Zhiyong Guan · 2026
Read Deep learning-driven automatic counting of petal number in cut chrysanthemum inflorescence by Shanpeng Xu, Jingshan Lu, Lian Ding, Fei Zhang, Fadi Chen, Zhenxing Wang, Sumei Chen, Weimin Fang, Zhiyong Guan (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/PMC13315742.txt.
Description
Shanpeng Xu and colleagues built a deep learning counter in 2026 for petals in cut chrysanthemum flower heads. Petal count helps judge quality and identify cultivars, but hand counting is slow and error-prone on such packed, partly hidden flowers, limiting large breeding programs.
Images from many varieties formed a training set, with density maps made by hand marking and smoothing. A congested-scene network strengthened with a squeeze-and-excitation attention block estimated petal density across the head. Counts agreed strongly with true petal numbers in their checks. Fast automatic counting could make flower phenotyping practical at scale.
Catalog record
| CREATOR | Shanpeng Xu, Jingshan Lu, Lian Ding, Fei Zhang, Fadi Chen, Zhenxing Wang, Sumei Chen, Weimin Fang, Zhiyong Guan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 81368 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |