Deep Learning Approach for Classifying Date Fruits Using YOLO: A Comparative Analysis

Object detection in agricultural automation is highly crucial in fruit management and optimization of resource utilization. This study conducts an in-depth performance evaluation of YOLO object detection algorithms such as YOLO version 8, YOLO version 9, and YOLO version 10 on identifying and classifying date fruits. Dates are agricultural products that are difficult to differentiate from one another due to their minute variations in color, shape, and texture. Date fruits form the basis of agricultural industries in countries like Saudi Arabia and the Middle East. They differ minimally in some of their physical properties, hence creating difficulties in their classification and sorting processes, which are very important in establishing the quality and edibility of dates harvested. Deep learning techniques are utilized in this work to implement the YOLO algorithm to automate the detection and classification of nine types of date fruits from 1,658 images. Precision and Recall metrics were applied to carefully examine every iteration of the improvement performance of the YOLO model. Among these, YOLO version 9 tends to be the most efficient model, having a Precision of $98.68 \%$, a Recall of 99.06%, with an overall Fitness of 99.5%. These metrics reflect the better capability of YOLO version 9 in sustaining high accuracy over a wide range of detection thresholds. Results prove the potential of YOLO version 9 to improve the efficiency of date fruit production industries by assuring early and correct fruit classification, reducing losses, and increasing productivity.