<![CDATA[Early detection of egg fertility is crucial for improving incubation efficiency and reducing energy waste in small-scale poultry farms. This study developed an automated sorting system using the YOLOv8n algorithm to detect and classify eggs into two classes: fertile and infertile. The dataset was collected through a candling process using images of 3- to 7-day-old chicken eggs taken under controlled lighting conditions. Data collection included acquiring original images, which were then manually annotated using a bounding box format in the collab platform to train the model to recognize embryo features. The YOLOv8n architecture was chosen for its superiority in fast feature extraction using an efficient backbone structure and neck system for real-time small object detection. Model performance was comprehensively evaluated using confusion matrix and mean average precision (mAP) metrics. The mAP value reached 0.995, precision 0.9, and recall 100% in the training phase. In live system testing using a webcam, the model produced stable confidence values in the range of 85% to 94% with an inference time of only 1.4 ms. The integration of intelligent models and servo actuators in the sorting system has been proven to be able to separate fertile and infertile eggs automatically with a high success rate.]]>
Copyrights © 2026
