Wood surface roughness, surface free energy (SFE), wettability, and bonding quality for water-based acrylic coatings were investigated. The samples tested in this study included Pinus radiata, Pinus sylvestris, Larch, Hemp oak, Catalpa tree, and Camphor. Sandpaper with grits of 180, 240, 320, 400, and 500 was utilized to sand wood surfaces. The van OSS-Chaudhury-Good equation (vOCG) was used to calculate the SFE values. The modified model (M-D) was used to calculate the wettability based on the contact angle change rate (K value). The higher the K value, the faster the contact angle approaches equilibrium. A cross-cut test was used to evaluate the coating’s bonding quality. The anatomical structure of wood has an impact on the roughness of hardwood. The equilibrium contact angle is influenced by the wood species and sandpaper grit size. Sanding can make the surface of wood more wettable. Radiata pine that had been sanded to 180 grit had the highest SFE value. After finishing with waterborne acrylic, hardwood had a slightly better coating adhesion than softwood. Hemp oak wood had the lowest coating adhesion (0.6) and the highest K value (0.82). The best bonding quality (0.4) was supplied by the camphor wood with the lowest K value (0.13). Wettability in terms of K values was a good indication of determining the bonding quality of the water-based acrylic coatings.

The swift and non-destructive classification of wood species holds crucial significance for the utilization and trade of wood resources. Portable near-infrared (NIR) spectrometers have the potential for rapid and non-destructive wood species identification, and while several studies have explored related methodologies, further research on their practical application is needed. To address this research gap, this study proposes a multi-scale convolutional neural network (CNN) combined with a portable NIR spectrometer (wavelengths range: 908 to 1676 nm) for wood species identification. To enhance the capability of directly extracting robust features from NIR spectral data collected by a portable spectrometer, the Gramian angular field (GAF) method is introduced to transform 1-dimensional (1D) NIR spectral data into 2-dimensional (2D) data matrices. Furthermore, a multi-scale CNN model is utilized for direct feature extraction. The representation by 2D matrices, instead of 1D NIR spectral data, aligns with 2D convolutional operations and enables a more robust extraction of discriminative features. In the experimental phase, eight wood species were identified using the proposed method, alongside commonly used multivariate data analysis and machine learning (ML) methods. The StratifiedGroupKFold dataset partitioning approach and five-fold cross-validation were used. Additionally, nine spectral preprocessing methods were compared, and principal component analysis (PCA) was used for feature extraction in the ML method. Evaluation metrics, such as accuracy, precision, and recall, were adopted to assess the performance of the methods. The proposed multi-scale CNN model, in combination with 2D GAF matrices of the 1D spectral data, yielded the most accurate results with a mean accuracy of 97.34% in the five-fold validation. These findings present a new approach for the construction of a rapid, non-destructive, and automatic wood species identification method using a portable NIR spectrometer.

Identifying wood accurately and rapidly is one of the best ways to prevent wood product fakes and adulterants in forestry products. Wood identification traditionally relies heavily on special experts that spend extensive time in the laboratory. A new method is proposed that uses near-infrared (NIR) spectra at a wavelength of 780–2300 nm incorporated with the gray-level co-occurrence (GLCM) texture feature to accurately and rapidly identify timbers. The NIR spectral features were determined by principal component analysis (PCA), and the digital image features extracted with the GLCM were used to create a support vector machine (SVM) model to identify the timbers. The results from fusion features of raw spectra and four GLCM features of 25 timbers showed that identification accuracy by the model was 99.43%. A sample anisotropy and heterogeneity comparative analysis revealed that the wood identification information from the transverse surface had more characteristics than that from the tangential and radial surfaces. Furthermore, short-wavelength pre-processed NIR bands of 780–1100 nm and 1100–2300 nm realized high identification accuracy of 99.43% and 100%, respectively. The four GLCM features were effective for improving identification accuracy by improving the data spatial clustering features.

Accurate and rapid wood species identification is vital for wood utilization and trade. This goal is achievable with the fast development of deep learning (DL). Several studies have been published related to this topic; however, they were limited by their generalization performance in practical applications. Therefore, this study proposed a DL multimodal fusion framework to bridge this gap. The study utilized a state-of-the-art convolutional neural network (CNN) to simultaneously extract both short-wavelength near-infrared (NIR) spectra and RGB image feature, fully leveraging the advantages of both data types. Using portable devices for collecting spectra and image data enhances the feasibility of onsite rapid identification. In particular, a two-branch CNN framework was developed to extract spectra and image features. For NIR spectra feature extraction, 1 dimensional NIR (1D NIR) spectra were innovatively encoded as 2 dimensional (2D) images using the Gramian angular difference field (GADF) method. This representation enhances better data alignment with CNN operations, facilitating more robust discriminative feature extraction. Moreover, wood’s spectral and image features were fused at the full connection layer for species identification. In the experimental phase conducted on 16 difficult-to-distinguish wood samples from the Lauraceae family, all achieved identification metrics results exceed 99 %. The findings illustrate that the proposed multimodal fusion framework effectively extracts and fully integrates the wood’s features, thereby, improving wood species identification.