Rapid seed viability prediction of Sophora japonica by improved successive projection algorithm and hyperspectral imaging

Abstract

Hyperspectral imaging technology (HSI) is considered to be a promising technology to detect and predict seed viability quickly and without damage. This research aimed to use HSI combined with deep learning methods to identify the seed viability of Sophora japonica. After simulating natural aging, high-viability, low-viability and non-viability seeds were distinguished, and then data collection continued for the first 10 h of seed imbibition. The validation set accuracy of machine learning methods (support vector machine (SVM) and random forest (RF)) without preprocessing was less than 80%, while the one-dimensional deep learning methods (convolutional neural network (CNN), recurrent neural network (RNN) and its superposition) were above 95%. An improvement was proposed on the basis of the original successive projection algorithm (SPA) and compared with three typical algorithms. When Autoregressive locally optimized successive projection algorithm (ALO-SPA) was combined with RNN, the detection model worked best. Therefore, based on this model, the vitality prediction was established using the data of swelling 0 h, and its effect was better than that of detection model. The results show that hyperspectral imaging combined with deep learning model can more accurately predict the seed viability of Sophora japonica.