Prediction of peanut seed vigor based on hyperspectral images

Abstract

Prediction of seed vigor based on hyperspectral peant. The traditional method is time-consuming and laborious to detect seed vigor. At the same time, the accuracy of the detection result is not high, and it will cause damage to the seed itself. Therefore, in order to achieve rapid and non-destructive detection of peanut seed vigor, the test was performed with original health, artificial aging for 24h and Peanut seeds with different vigor gradients at 72 hours were used as the research samples. Hyperspectral images with a wavelength range of 387~1035 nm were collected, and the image of the central part of the peanut seeds with a pixel size of 60 × 60 after correction was intercepted and the average reflectance value was calculated. After a combination of processing analysis, characteristic band processing, and model selection, a hyperspectral prediction system with the highest correlation to the viability of extracted peanut seeds was finally established. Experiments shown that the combination of hyperspectral imaging technology and the MF-LightGBM-RF model had the best performance, with a prediction accuracy of 92.59% and a fitting time of 1.77s, which simplifies the model and improves efficiency.

Keywords:
hyperspectral; predictive modeling; seed viability; non-destructive testing techniques