Strawberry Ripeness Detection Using Deep Learning Models

Abstract

In agriculture, the timely and accurate assessment of fruit ripeness is crucial to optimizing harvest planning and reduce waste. In this article, we explore the integration of two cutting-edge deep learning models, YOLOv9 and Swin Transformer, to develop a complex model for detecting strawberry ripeness. Trained and tested on a specially curated dataset, our model achieves a mean precision (mAP) of 87.3% by using the metric intersection over union (IoU) at a threshold of 0.5. This outperforms the model using YOLOv9 alone, which achieves an mAP of 86.1%. Our model also demonstrated improved precision and recall, with precision rising to 85.3% and recall rising to 84.0%, reflecting its ability to accurately and consistently detect different stages of strawberry ripeness.

Keywords

• transformer
• YOLOv9
• Swin Transformer
• deep learning
• computer vision