AI-powered detection and quantification of post-harvest physiological deterioration (PPD) in cassava using YOLO foundation models and K-means clustering
Daniela Gómez Ayalde, Juan Camilo Giraldo Londoño, Audberto Quiroga Mosquera, Jorge Luis Luna Melendez, Winnie Gimode, Thierry Tran, Xiaofei Zhang, Michael Gomez Selvaraj · 2024
Read AI-powered detection and quantification of post-harvest physiological deterioration (PPD) in cassava using YOLO foundation models and K-means clustering by Daniela Gómez Ayalde, Juan Camilo Giraldo Londoño, Audberto Quiroga Mosquera, Jorge Luis Luna Melendez, Winnie Gimode, Thierry Tran, Xiaofei Zhang, Michael Gomez Selvaraj (2024) 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-11585225.txt.
Description
Ayalde and a large team train AI models to grade spoilage in stored cassava roots from photos in twenty twenty-four. Cassava roots decay fast after harvest, which costs farmers and processors dearly. Scoring the decay by eye is slow and hard to keep uniform. Their system sorts phone or camera images by level of decay.
Several top image models were tried, and one led on overall scoring. A second model was best at spotting sound roots but trained unevenly. Extra steps that cut out off color zones shrank scoring error a lot. The tools let breeders screen roots fast and pick lines that resist decay. That supports food security where cassava is a staple.
Catalog record
| CREATOR | Daniela Gómez Ayalde, Juan Camilo Giraldo Londoño, Audberto Quiroga Mosquera, Jorge Luis Luna Melendez, Winnie Gimode, Thierry Tran, Xiaofei Zhang, Michael Gomez Selvaraj |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 75 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |