Real Time Chicken Egg Size Classification Using Yolov4 Algorithm

The common problem currently faced by MSMEs producing chicken eggs is experiencing difficulties in grouping egg sizes every day. Currently, grouping egg sizes is still done manually, this is less than optimal and prone to errors so that many business owners often experience losses. Grouping egg sizes before being sold is very important to note because each size affects the selling price of eggs. The use of technology on a MSME scale in laying hen farmers has not been widely adopted, this is due to limited access and understanding of technology so that to improve and strengthen productivity, management, and marketing in this business, technological innovation is needed. One alternative solution to deal with this problem is to build a real-time computerized system that can group eggs according to their size. This study aims to evaluate the performance of the Yolov4 algorithm in grouping egg sizes based on their size in real time. Based on the results of the tests carried out, the Yolov4 algorithm is able to group chicken eggs in real time with an F1-Score value: 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 size grouping application that can help MSMEs to monitor the productivity of chicken eggs every day.