PERBANDINGAN ALGORITMA YOLOV3 DAN YOLOV4 DALAM PENGELOMPOKAN UKURAN TELUR AYAM SECARA REAL TIME

The common problem currently faced by MSMEs producing chicken eggs is the difficulty in calculating the number of eggs and grouping egg sizes where everything is still done manually so that errors often occur and many entrepreneurs often experience losses. To improve and strengthen productivity, management, and marketing in this business, technological innovation is needed. This study aims to detect the number of eggs and group egg sizes based on their type using the Yolov3 and Yolov4 algorithms. Based on the results of the tests carried out, it shows that the Yolov3 and Yolov4 algorithms are able to detect chicken eggs in real time with the best accuracy value obtained by the Yolov3 algorithm. The comparison was carried out using 10 epoch tests with an F1-Score value of 0.89 where the F1-Score value approaching 1 indicates that the system performance has been running well. The results of this classification can be used to create a real time egg calculation application that can help calculate the number of eggs every day by each MSME.