<![CDATA[In the agricultural sector, accurately determining fruit ripeness remains a crucial yet challenging task. Among intriguing Indonesian fruits, the Ambarella presents a particular difficulty. In Ambarella fruit, the peel changes from green to golden yellow as it ripens, serving as a visual indicator for optimal harvest time, thus determining the maturity is crucial for harvesting the Ambarella fruit. Traditionally, ripeness assessment relies on manual methods, which suffer from drawbacks like high labor costs, significant time investment, and inconsistency in results. This work explores the potential of employing YOLOv8, a cutting-edge deep learning model, to automate Ambarella fruit ripeness classification. This work focuses on the YOLOv8n, YOLOv8s, and YOLOv8m, lightweight models within the YOLOv8 family. Our results are promising: all three models achieved 100% accuracy on the training set, with YOLOv8s demonstrating the lowest loss at 0.00286. The web application was utilised to deploy the trained models, allowing users to upload images of Ambarella fruit and run the model for inference.]]>
Copyrights © 2024
