A Vision-Based Fruit Packaging Robot

Abstract

The rapid development of computer vision makes human-computer interaction possible and has a wide application prospect. Since the first case of COVID-19 was found, up to now, the global number of infected people has reached 119220681 [1]. In China, although the epidemic is under control, affected by the external environment, the epidemic will also spread through cold chain transportation, and imported fruits may also carry the virus. In order to solve this problem, based on deep learning, we collected 300 fruit images and used YOLOV5 to recognize some common fruit images. The experimental results are shown in the proposed method, and the average accuracy can reach about 84%.