Abstract: A apricot hot air drying control system based on machine vision was proposed, which used computer vision technology to detect and categorize apricots and automatically control temperature and wind speed in hot air drying process．The system used a neural network-based target detection algorithm to detect and segment apricots, extracted features of apricots using image processing technology, and classified apricots using YOLOv7．By adjusting parameters of temperature, wind speed and time of hot air drying, quality protection of apricot drying process was realized, which could maintain quality and taste of apricot and enhance economic value of dried apricot, and the system has certain application prospects．