RT info:eu-repo/semantics/article
T1 Deep learning to classify the ripeness of coffee fruit in the mechanized harvesting process
A1 Zanella, Marco Antonio
A1 Barrio Conde, Mikel
A1 Gómez Gil, Jaime
A1 Aguiar Pérez, Javier Manuel
A1 Pérez Juárez, María Ángeles
A1 Silva, Fabio Moreira de
K1 Ciencias agrarias
K1 Cultivo de café
K1 Procesos mecanizados de cosecha
K1 Deep Learning
K1 YOLO
K1 Cultivo de café
K1 Detección de frutos
K1 Agricultura de precisión
K1 31 Ciencias Agrarias
K1 1203.04 Inteligencia Artificial
AB The coffee industry is a vital sector of global agriculture. Coffee is one ofthe most widely traded plant products in the world. Coffee fruit ripeness affects the tasteand aroma of the final brewed beverage, coffee farms’ overall yield and economic viability.Traditional methods of assessing coffee fruit ripeness, which rely on manual inspection byskilled workers, are labor-intensive, time-consuming, and prone to subjective interpretation.In this study, we have used the YOLOv9 (You Only Look Once) algorithm that outperformedprevious versions particularly by using a new lightweight network architecture called thegelan-c model. The objective of this study was to identify and classify quickly and accuratelythe degree of ripeness of the harvested coffee fruits into the following classes: unripe,ripe-red, ripe-yellow, and overripe. The images were captured during harvesting with acommercial harvester in a coffee farm in the southern region of the state of Minas Gerais,Brazil. Data augmentation was performed to increase the dataset in terms of imagesand bounding boxes. Detection performance was obtained for image sizes between 128and 640 px. The best performance was achieved with an image size of 640 px, reachinga precision level of 99 %, a recall of 98.5 %, an F1-Score of 98.75 %, a mAP@0.5 of99.25 %, and a mAP@0.5:0.95 of about 85 % during the validation phase. Our studysignificantly outperforms previous studies on fruit classification in terms of models used,data augmentation strategies, and overall performance.
PB Piracicaba SP: Universidade de São Paulo Escola Superior de Agricultura Luiz de Queiroz
SN 1678-992X
YR 2025
FD 2025
LK https://uvadoc.uva.es/handle/10324/81785
UL https://uvadoc.uva.es/handle/10324/81785
LA eng
NO Scientia Agricola, 2025, vol. 82.
NO Producción Científica
DS UVaDOC
RD 30-ene-2026