A Novel Public Dataset for Strawberry (Fragaria × Ananassa) Ripeness Detection and Comparative Evaluation of YOLO-Based Models.

The strawberry (Fragaria × ananassa), known worldwide for its economic value and nutritional richness, is a widely cultivated fruit. Determining the correct ripeness level during the harvest period is crucial for both preventing losses for producers and ensuring consumers receive a quality product. However, traditional methods, that is, visual assessments alone, can be subjective and have a high margin of error. Therefore, computer-assisted systems are needed. However, the scarcity of comprehensive datasets accessible to everyone in the literature makes it difficult to compare studies in this field. In this study, a new and publicly available strawberry ripeness dataset, consisting of 566 images and 1169 labeled objects across three ripeness classes (fully-ripe, semi-ripe, and unripe), prepared under variable light and environmental conditions in two different greenhouses in Turkey, is presented to the literature. Comparative tests conducted on the dataset using twelve YOLOv8, YOLOv9, and YOLO11 detection variants showed that the highest precision value was 90.94% in the YOLOv9c model, while the highest recall value was 83.74% in the YOLO11s model. In terms of the general performance criterion mAP@50, YOLOv8s was the best performing model with a success rate of 86.09% (mAP@50:95 = 75.52%). On this dataset, smaller and medium-sized models (approximately 10-12 million parameters, e.g., YOLOv8s and YOLO11s) achieved accuracy comparable to the largest variants at substantially lower computational cost and higher inference speed, establishing a reproducible reference point for smart-agriculture applications. These findings are specific to the present dataset and should be validated on larger, more diverse data before being generalized.