Application of visible and short-wave near-infrared spectroscopy for discrimination of tomato leaves with different genes

Abstract

The feasibility of using visible and short-wave near-infrared (Vis/SW NIR) diffuse reflectance spectroscopic technique in the 450-950 nm region to classify tomato leaves with different genes was investigated. In this study, four hundred and six tomato leaves were measured. Different chemometrics techniques, including discriminant analysis (DA), soft independent modeling of class analogy (SIMCA), discriminant partial least-squares (DPLS) were applied to classify samples. The samples were randomly split into two sets, one used as a calibration set and the remaining samples as a validation set. The discrimination performance of these chemometrics techniques was compared. The results show that DA and DPLS with derivative has the excellent performance, 100% of success rate. The results show that Vis/SW NIR diffuse reflectance spectroscopic technique can be used to classify tomato leaves with different genes.