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 Gomez-Gil, Jaime
A1 Aguiar-Perez, Javier Manuel
A1 Pérez-Juárez, María Ángeles
A1 da Silva, Pablo Moreira
K1 Agricultura de precisión
K1 Machine learning
K1 Aprendizaje automático
K1 Sustainable agriculture
K1 Agricultural innovations
K1 Agricultura - Innovaciones tecnológicas
K1 Neural networks (Computer science)
K1 Computer vision
K1 Visión artificial (Robótica)
K1 Agricultural engineering
K1 Agriculture
K1 YOLO
K1 coffee farming
K1 fruit detection
K1 precision agriculture
K1 3102 Ingeniería Agrícola
K1 1203.04 Inteligencia Artificial
K1 3325 Tecnología de las Telecomunicaciones
K1 1203.17 Informática
AB The coffee industry is a vital sector of global agriculture. Coffee is one of the most widely traded plant products in the world. Coffee fruit ripeness affects the taste and 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 by skilled 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 outperformed previous versions particularly by using a new lightweight network architecture called the gelan-c model. The objective of this study was to identify and classify quickly and accurately the 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 a commercial 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 images and bounding boxes. Detection performance was obtained for image sizes between 128 and 640 px. The best performance was achieved with an image size of 640 px, reaching a precision level of 99 %, a recall of 98.5 %, an F1-Score of 98.75 %, a mAP@0.5 of 99.25 %, and a mAP@0.5:0.95 of about 85 % during the validation phase. Our study significantly outperforms previous studies on fruit classification in terms of models used, data augmentation strategies, and overall performance.
PB ScIELO
SN 1678-992X
YR 2025
FD 2025
LK https://uvadoc.uva.es/handle/10324/83819
UL https://uvadoc.uva.es/handle/10324/83819
LA eng
NO Scientia Agricola, 2025, vol. 82, n. 1, 1-7
NO Producción Científica
DS UVaDOC
RD 28-mar-2026