The design and experiment of peanut high-throughput automatic seed testing system based on machine learning

ABSTRACT In view of the fact that the current peanut test was still artificial, it was difficult to meet the actual demand of peanut test, this paper established a peanut high-throughput automatic test system (automatic measurement), which improves the work efficiency of peanut test. The system mainly included peanut automatic seed testing device, scanning gun, industrial computer, multi-serial controller and peanut automatic seed testing system, which could obtain the automation of the whole process of peanut pod testing and kernel fruit testing in real time. The results showed that the system can measure the peanut pods and nuts and other parameters in real time, and the average measuring accuracy of the length, width, diameter and quantity of the peanut pod and kernel was more than 98%. Compared with the manual test, the automatic measurement can significantly improved the test efficiency. The system was also suitable for the acquisition of other crop test parameters and provides a reference for high-throughput automatic test.