딥러닝을 이용한 푸른 사과 낙과 검출 시스템 개발

Recently deep learning that shows high performance in the image recognition requires high-performance hardware and it takes a lot of time in the learning and detecting it. In the limited environment, it is inefficient for deep learning with excessive amount of computation to detect all areas of the high-resolution. It is suggested one should reduce unnecessary alternatives by applying the image processing using the edge analysis and MCT conversion, and use deep learning in order to improve accuracy in detection.