Identifying Wood Based on Near-Infrared Spectra and Four Gray-Level Co-Occurrence Matrix Texture Features

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.

Comparative wood anatomy of 15 Malagasy Diospyros species (Ebenaceae)

Diospyros L. (Ebenaceae) is an important source of ebony, a precious wood used for several economically important timber products. Species are overexploited in many regions, including Madagascar, for both the national and international trade, but little is known about their wood anatomy, despite its importance for forensic identification. Wood anatomy has a major role to play in ensuring the sustainable and equitable utilization of Diospyros species that are not threatened by extinction, and in law enforcement to protect threatened species from illegal logging. This study aims to identify, describe, and test the usefulness of anatomical features to support a taxonomic revision of the genus in Madagascar and to enrich databases for wood identification. Ninety-nine wood specimens were collected from the various bio-geographical regions of Madagascar, representing 15 endemic species (twelve previously described and three new) of large trees (reaching DBH ⩾ 20 cm and/or height ⩾ 20 m) were investigated. Standard methods for wood anatomical studies were used. Statistical analysis of the data using Factorial Analysis on Mixed Data was performed for 14 wood anatomical characters. Detailed descriptions and comparisons of the wood anatomy of the 15 species are provided, along with a wood identification key. Analyses showed that all the characters are highly significant () in the separation of the species studies.

Wood Identification of Ancient Temple Structures in Ladakh, Located in the Western Himalayas

Microscopic wood identifications were performed on five Buddhist temple structures, three vernacular houses, two stupas, and two holy trees located in Ladakh, a region in the Indian state of Jammu and Kashmir in the Western Himalayas. Leh is Ladakh’s capital and is located along the Indus River, the backbone of Ladakh. The vernacular buildings, stupa, and holy trees are located in Leh. Ladakh is a high-altitude desert with extremely scarce vegetation. Natural vegetation occurs mostly along the watercourses. The temples are located in villages along the upper Indus river valley, or along confluent rivers. From the 110 wood samples, 4 wood species were identified: poplar, willow, juniper, and pine. Building type, local availability, specific physical and mechanical properties of the wood species, and religious considerations were apparently the leading criteria for timber selection.

Field-Deployable Computer Vision Wood Identification of Peruvian Timbers

Illegal logging is a major threat to forests in Peru, in the Amazon more broadly, and in the tropics globally. In Peru alone, more than two thirds of logging concessions showed unauthorized tree harvesting in natural protected areas and indigenous territories, and in 2016 more than half of exported lumber was of illegal origin. To help combat illegal logging and support legal timber trade in Peru we trained a convolutional neural network using transfer learning on images obtained from specimens in six xylaria using the open source, field-deployable XyloTron platform, for the classification of 228 Peruvian species into 24 anatomically informed and contextually relevant classes. The trained models achieved accuracies of 97% for five-fold cross validation, and 86.5 and 92.4% for top-1 and top-2 classification, respectively, on unique independent specimens from a xylarium that did not contribute training data. These results are the first multi-site, multi-user, multi-system-instantiation study for a national scale, computer vision wood identification system evaluated on independent scientific wood specimens. We demonstrate system readiness for evaluation in real-world field screening scenarios using this accurate, affordable, and scalable technology for monitoring, incentivizing, and monetizing legal and sustainable wood value chains.

Wood microscopic image identification method based on convolution neural network

To prevent the illegal trade of precious wood in circulation, a wood species identification method based on convolutional neural network (CNN), namely PWoodIDNet (Precise Wood Specifications Identification) model, is proposed. In this paper, the PWoodIDNet model for the identification of rare tree species is constructed to reduce network parameters by decomposing convolutional kernel, prevent overfitting, enrich the diversity of features, and improve the performance of the model. The results showed that the PWoodIDNet model can effectively improve the generalization ability, the characterization ability of detail features, and the recognition accuracy, and effectively improve the classification of wood identification. PWoodIDNet was used to analyze the identification accuracy of microscopic images of 16 kinds of wood, and the identification accuracy reached 99%, which was higher than the identification accuracy of several existing classical convolutional neural network models. In addition, the PWoodIDNet model was analyzed to verify the feasibility and effectiveness of the PWoodIDNet model as a wood identification method, which can provide a new direction and technical solution for the field of wood identification.

Computer vision-based wood identification and its expansion and contribution potentials in wood science: A review

The remarkable developments in computer vision and machine learning have changed the methodologies of many scientific disciplines. They have also created a new research field in wood science called computer vision-based wood identification, which is making steady progress towards the goal of building automated wood identification systems to meet the needs of the wood industry and market. Nevertheless, computer vision-based wood identification is still only a small area in wood science and is still unfamiliar to many wood anatomists. To familiarize wood scientists with the artificial intelligence-assisted wood anatomy and engineering methods, we have reviewed the published mainstream studies that used or developed machine learning procedures. This review could help researchers understand computer vision and machine learning techniques for wood identification and choose appropriate techniques or strategies for their study objectives in wood science.