SVM Classification Method of Waxy Corn Seeds with Different Vitality Levels Based on Hyperspectral Imaging

The vitality of corn seeds is a significant indicator for assessing the quality and yield crops. In recent years, numerous information technologies have been adopted to analyze seed provide support efficient equipment. However, there are still some shortcomings in these technologies, which decrease accuracy identifying various practical applications. this paper, synthesized classification method was proposed based on multisensor hyperspectral imaging. Firstly, images range 370-1042 nm were collected waxy seeds, subjected aging processing with four periods time (0, 3, 6, 9 d). Besides, preprocessing techniques including standard normal variate, multiplicative scatter correction, Savitzky-Golay smoothing, first-order second-order derivatives employed suppress noise interference raw spectra. addition, principal component analysis (PCA), 2nd derivatization, successive projection algorithm (SPA) select feature wavelengths. Moreover, SVM models full spectra wavelengths established. results showed that, selected by SPA, model preprocessed correction (MSC) had optimal performance. training testing 100% 97.9167%, respectively. RMSE 0.018 R 2 0.875. Therefore, it can be demonstrated that pattern recognition could achieve high classifying accelerated seeds. This provides new machine learning (ML) nondestructive detection