A Real-time Artificial Intelligence Recognition System on Contaminated Eggs for Egg Selection

Abstract

A real-time artificial intelligence (AI) recognition system is newly used for applications of selecting unqualified in chicken cages. The proposed recognition system can detect dirty eggs from those clean ones by using the developed artificial intelligence. Furthermore, the recognition system can classify those contaminated eggs into three categories by a covered contamination area. Performing this functionality of the proposed real-time AI recognition system, the system can successfully detect unqualified eggs in cage. In addition, by deleting the unnecessary predicted bounding boxes and performing the non-maximum suppression algorithm utilized in the experiment, the time spending on every picture will be fewer than normal videos. The proposed recognition system could be used for selecting unqualified eggs applications.