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

Abstract

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

Visible/near-infrared hyperspectral imaging combined with machine learning for identification of ten Dalbergia species

“…By capturing extensive chemical and spatial information across Vis to NIR spectra, HSI enables researchers to detect subtle differences in species and materials through their unique biochemical signatures. This technology is particularly effective in wood science, where it provides detailed insights into the microscopic structure and chemical alterations of wood, allowing for the identification of key constituents like lignin and cellulose which are crucial for assessing wood's mechanical properties and durability (Wang et al, 2022;Xue et al, 2022Xue et al, , 2023. Despite facing challenges related to data storage and processing demands, the future of HSI in these diverse applications looks promising, thanks to ongoing advancements in sensor technology and algorithm development aimed at enhancing data handling and robustness (Amaral et al, 2021).…”

Unsupervised Wood Species Identification Based on Multiobjective Optimal Clustering and Feature Fusion

“…With the rapid development of pattern recognition and image processing technology, integrating of pattern recognition and spectral technology for clustering detection has become widespread, offering a novel approach for wood identification. Visible light/near-infrared (Vis/NIR) hyperspectral imaging (HSI) was utilized to identify Pterocarpus santalinus and nine other counterfeit wood samples, and it was found that a classification model combining squared SVM with a normalization preprocessing method could achieve a prediction accuracy higher than 99.8% across the spectral range (400-2500 nm) (Xue et al 2023). Differences in stem bark texture between tree species were investigated using a hyperspectral camera set-up and gray-level co-occurrence matrices, and the analyses were based on 200 hyperspectral reflectance data cubes representing ten tree species.…”