Identification of Eight Pterocarpus Species and Two Dalbergia Species Using Visible/Near-Infrared (Vis/NIR) Hyperspectral Imaging (HSI)

Pterocarpus santalinus is considered among the finest luxury woods in world and has potential commercial medicinal value. Due to its rich hue high price, often been substituted mislabeled with other of lower economic To maintain order timber market interests consumers, it necessary establish a fast reliable method for species identification. In this study, wood samples nine commonly used counterfeiting were analyzed by visible light/near-infrared (Vis/NIR) hyperspectral imaging (HSI). The spectral data preprocessed different algorithms. Principal component analysis (PCA) was applied ranges: 400~2500 nm, 400~800 800~2500 nm. Partial least squares discriminant (PLS-DA) square support vector machine (SVM) modeling methods performed effective discrimination. best classification model SVM combined normalization preprocessing whole range (400~2500 nm), prediction accuracy higher than 99.8%. results suggest that use Vis/NIR-HSI combination chemometric approaches can be as an tool discrimination santalinus.