Development of Visual Egg Inspection System for Poultry Farmer Using CNN with Deep Learning

We have developed an automatic visual egg inspection system for poultry farmers. The egg inspection system used by the aggregator in Japan is a large-scale system, and it is difficult for general poultry farmers to introduce a similar system. Under such circumstances, the small-scale automatic inspection system for small scale poultry farmers is desired. The developed system can detect the defective eggs moving on the conveyor in the same environment as human worker. In this system, the appearance of egg is detected by image sensor and its dirt or cracks are detected using convolutional neural network (CNN) with deep learning. Moreover, the system can indicate the result on the screen within very short time with high accuracy. The effectiveness of the proposed system is confirmed by experiments.