Identification Of Wood Species Research Articles

WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images

Wood species identification plays a crucial role in various industries, from ensuring the legality of timber products to advancing ecological conservation efforts. This paper introduces WoodYOLO, a novel object detection algorithm specifically designed for microscopic wood fiber analysis. Our approach adapts the YOLO architecture to address the challenges posed by large, high-resolution microscopy images and the need for high recall in localization of the cell type of interest (vessel elements). Our results show that WoodYOLO significantly outperforms state-of-the-art models, achieving performance gains of 12.9% and 6.5% in F2 score over YOLOv10 and YOLOv7, respectively. This improvement in automated wood cell type localization capabilities contributes to enhancing regulatory compliance, supporting sustainable forestry practices, and promoting biodiversity conservation efforts globally.

Chemotaxonomic and anatomic wood species identification in bleached pulp: blind test and method validation

Abstract This paper presents a comparative analysis of the blind test outcomes of two independent methods for the identification of tropical wood species in pulp and paper products. Both, the established anatomical and the relatively new chemotaxonomic method support the European Deforestation Regulation 2023/1115 (EUDR), which aims to ensure that only legally harvested timber that has not contributed to deforestation is traded in the EU. The blind test involved 570 decisions on 15 test sheets of 37 self-manufactured mixed tropical hardwood pulps and an industrial beech pulp, used as a matrix. Both detection techniques demonstrated robust performance with over 80 % hit rates. The results show that the synergies and combination of the strengths of both methods can be utilized and lead to even better combined performance. In order to establish the chemotaxonomic identification method as a complement to the conventional anatomy-based method, statistical analyses were performed to assess its intermediate precision between three different GC-MS systems. In most cases, the method gave consistent results independent of the instrument used.

The utilization of wood samples from xylarium in historical wooden statues: improving the separation accuracy non-destructive measurement for using several algorithms

There are numerous wooden historical artifacts in Kyoto and other parts of Japan, including Buddhist statues or Shinto deities. The identification of wood species in these historical artifact is desirable for both repair and maintenance purposes. The most common method of identifying wood species involves examining samples taken from the artifacts. However, intentional sampling from old cultural artifacts is prohibited in Japan. As a result, we attempted to determine the wood species of old statues non-destructively using near-infrared spectroscopy (NIRS). In this article, we developed the softwood and hardwood separation model using NIRS to compare the prediction accuracy for few algorithms. The model was created based on wood samples stored in the xylarium of the Forestry and Forest Products Research Institute (TWTw). We then applied this model to old Buddhist statues in order to classify them as either softwood or hardwood. These Buddhist statues were housed in Nazenji temple and are believed to have been carved during the Heian period (8th–12th century). For the near-infrared (NIR) measurements, we collected diffuse reflectance spectra from TWTw sample and Buddhist statues using same spectrometer. Initially, we used the soft independent modeling of class analogy method (SIMCA), partial least squares discriminant analysis (PLS_DA), and support vector machine to analyze the NIR spectra obtained from the TWTw wood samples. Subsequently, we applied the NIR spectra obtained from several Buddhist statues in Nazenji temple to the aforementioned separation model and determined whether spectra data were classified as the softwood or hardwood. Finally, wood specimens detached naturally from the Buddhist statues over time were observed under microscopic analysis to identify the wood species. As comparing the prediction accuracy of few algorithms, SIMCA had a poor result, but PLS_DA had a good result. PLS_DA had better discrimination because it performed calculations to improve regression from both explanatory variables and objective variables.

Evaluation of Deterioration Degree of Archaeological Wood from Luoyang Canal No. 1 Ancient Ship

This study provides a detailed investigation of archaeological wood samples from the Luoyang Canal No. 1 site, focusing on wood species identification, physical properties, mechanical property analyses, and morphological examination. The identified wood species, belonging to the Ulmus genus, exhibited a 43% decline in compressive strength in waterlogged environments. Further, the wood exhibited increased moisture content, higher porosity, reduced basic density, and elevated shrinkage rates, indicating a mild level of degradation. X-ray diffraction was employed for the observation of cellulose structure, and Fourier transform infrared spectroscopy (FT-IR) demonstrated significant removal of cellulose and hemicellulose components. These findings emphasize the importance of understanding wood degradation mechanisms to evaluate structural integrity and durability in guiding the development of effective preservation strategies for archaeological wood artifacts. Continued research and conservation are crucial to deepen our knowledge of wood deterioration processes and enhance the implementation of preservation techniques.

Validation study on the practical accuracy of wood species identification via deep learning from visible microscopic images

This study aimed to validate the accuracy of identifying Japanese hardwood species from microscopic cross-sectional images using convolutional neural networks (CNN). The overarching goal is to create a versatile model that can handle microscopic cross-sectional images of wood. To gauge the practical accuracy, a comprehensive database of microscopic images of Japanese hardwood species was provided by the Forest Research and Management Organization. These images, captured from various positions on wood blocks, different trees, and diverse production areas, resulted in substantial intra-species image variation. To assess the effect of data distribution on accuracy, two datasets, D1 and D2, representing a segregated and a non-segregated dataset, respectively—from 1,000 images (20 images from each of the 50 species) were compiled. For D1, distinct images were allocated to the training, validation, and testing sets. However, in D2, the same images were used for both training and testing. Furthermore, the influence of the evaluation methodology on the identification accuracy was investigated by comparing two approaches: patch evaluation and E2 image evaluation. The accuracy of the model for uniformly sized images was approximately 90%, whereas that for variably sized images it was approximately 70%.

Phytochemical Profile of Rhizophora apiculata, Bruguiera gymnorhiza, and Bruguiera cylindrica for Wood Identification

Identification of wood species that are difficult to distinguish from their anatomical structure can be done through phytochemical (extractive substance) profiling. This research aimed to analyze the phytochemical profile as a sorter for three species of mangrove wood from Indramayu and Cilacap Regencies, Indonesia, using the liquid chromatography-mass spectrum. The phytochemical markers of taxonomic were the dominant compounds only found in one wood species. The results showed that the three types of wood are dominated by phytochemicals dissolved in ethanol. The results of LCMS analysis of the ethanol extract showed that the phytochemical markers were triterpenoid, flavonoid, and fatty acyls glycoside groups for Rhizophora apiculata, steroid and naphthalene groups for Bruguiera gymnorhiza, and alkaloid as well as fatty amide group for Bruguiera cylindrica. The dominant compounds that characterize these can be used in sorting between mangrove wood species. Keywords: characterizer, compound, mangrove, phytochemicals

A comparative study on the performance of terahertz, near-infrared, and hyperspectral spectroscopy for wood identification

ABSTRACT Wood species identification is of paramount significance in wood products manufacturing and applications. In contrast to traditional wood identification methods, spectroscopy-based technology offers a rapid, cost-effective, and efficient alternative. This study focuses on five wood species as experimental materials and aims to obtain three distinct wood spectra for each: near-infrared (NIR) spectra, hyperspectral image spectral information, and terahertz (THz) spectra. These spectra underwent pre-processing techniques such as Savitzky–Golay smoothing (SG), normalization, multiple scattering correction (MSC), and standard normalized variate (SNV), followed by dimensionality reduction through principal component analysis (PCA). Subsequently, the processed data were input into a partial least squares discriminant analysis (PLS-DA) for recognition. The results demonstrate the best recognition accuracy of 99.8% for THz spectra, 98.7% for NIR spectra, and 97.3% for hyperspectral image spectral information. The THz spectra exhibited the highest recognition accuracy, particularly with the SG-preprocessed THz spectra. These preprocessed spectra effectively removed noise and smoothed the spectral curves compared to the raw spectra.

Opening the black box: explainable deep-learning classification of wood microscopic image of endangered tree species

BackgroundTraditional method of wood species identification involves the use of hand lens by wood anatomists, which is a time-consuming method that usually identifies only at the genetic level. Computer vision method can achieve "species" level identification but cannot provide an explanation on what features are used for the identification. Thus, in this study, we used computer vision methods coupled with deep learning to reveal interspecific differences between closely related tree species.ResultA total of 850 images were collected from the cross and tangential sections of 15 wood species. These images were used to construct a deep-learning model to discriminate wood species, and a classification accuracy of 99.3% was obtained. The key features between species in machine identification were targeted by feature visualization methods, mainly the axial parenchyma arrangements and vessel in cross section and the wood ray in tangential section. Moreover, the degree of importance of the vessels of different tree species in the cross-section images was determined by the manual feature labeling method. The results showed that vessels play an important role in the identification of Dalbergia, Pterocarpus, Swartzia, Carapa, and Cedrela, but exhibited limited resolutions on discriminating Swietenia species.ConclusionThe research results provide a computer-assisted tool for identifying endangered tree species in laboratory scenarios, which can be used to combat illegal logging and related trade and contribute to the implementation of CITES convention and the conservation of global biodiversity.

ATR-FTIR spectroscopy and Machine learning for sustainable wood sourcing and species Identification: Applications to wood forensics

Wood forensics, a vital tool in addressing global concerns surrounding illegal logging and the authenticity of wood products, plays a pivotal role in promoting sustainable forestry practices. The integration of Attenuated Total Reflectance Fourier-Transform Infrared (ATR-FTIR) spectroscopy and machine learning presents a potent approach to streamline identification processes and enhance responsible wood sourcing. ATR-FTIR facilitates the detailed characterization of wood components by analyzing spectral data, revealing unique chemical signatures associated with different wood species. This study focuses on Eucalyptus, Dalbergia, and Populus wood species in India, revealing common peaks related to cellulose, flavones, hemicellulose, and lignin constituents. Isolation Forest (iForest) identifies outliers, subsequently removed for supervised modelling, while Principal Component Analysis (PCA) reduces dimensionality effectively. Tree-based supervised machine learning algorithms, including Decision Tree, Extra Tree, Random Forest, and CatBoost classifiers, enhances the accuracy of wood species discrimination by deciphering complex patterns within ATR-FTIR spectra. Further, evaluation through various performance metrics supports the comparative analysis. The outcomes of this study hold significant value for law enforcement agencies in combating illegal logging and timber trade, and potential applications in quality control for timber industries. This research substantiates its real-world applicability, marking a noteworthy advancement in the evolving field of wood forensics.

A Multi-Scale Convolutional Neural Network Combined with a Portable Near-Infrared Spectrometer for the Rapid, Non-Destructive Identification of Wood Species

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.

Wood Quality Analyzing System

This paper presents a comprehensive approach to optimizing furniture design processes and facilitating wood identification through the development of a mobile application. The application is designed to provide users with intuitive tools and resources for informed decisionmaking in furniture design and wood selection. The first component of the mobile application focuses on optimizing furniture design through furniture size and quality consideration. This encompasses the creation of an intuitive user interface that enables users to specify their furniture design preferences, including material selection criteria. A comprehensive wood database is meticulously curated, furnishing users with comprehensive details on wood sizes, qualities, and thicknesses, thereby aiding in material selection and waste reduction initiatives. Algorithms are employed to recommend optimal wood sizes, considering factors such as material selection, waste reduction, and cost analysis. Visual representation tools are included, allowing users to preview furniture designs with different wood options, facilitating informed decisionmaking. Furthermore, feedback mechanisms have been integrated to enable users to provide feedback on recommended wood sizes and qualities, thereby facilitating continuous enhancement and refinement of recommendations. The second component aims to identify the type of wood by its appearance. Image processing features have been developed to precisely extract visual characteristics from wood sample images, thereby aiding in the identification of wood species. Machine learning models are trained to classify wood species based on visual characteristics obtained from images, thereby enhancing the precision of identification. User interaction tools have been designed to ensure ease of use and accessibility for users in capturing and submitting wood sample images. Within the application, educational resources and materials are provided to help users learn about different wood species, aiding their understanding and selection process.

Making wood inspection easier: FTIR spectroscopy and machine learning for Brazilian native commercial wood species identification.

The molecular structure of wood is mainly based on cellulose, lignin, and hemicellulose. However, low concentrations of lipids, phenolic compounds, terpenoids, fatty acids, resin acids, and waxes can also be found. In general, their color, smell, texture, quantity, and distribution of pores are used in human sensory analysis to identify native wood species, which may lead to erroneous classification, impairing quality control and inspection of commercialized wood. This study developed a fast and accurate method to discriminate Brazilian native commercial wood species using Fourier Transform Infrared Spectroscopy (FTIR) and machine learning algorithms. It not only solves the limitations of traditional methods but also goes beyond as it allows fast analyses to be obtained at low cost and high accuracy. In this work, we provide the identification of five Brazilian native wood species: Angelim-pedra (Hymenolobium petraeum Ducke), Cambara (Gochnatia polymorpha), Cedrinho (Erisma uncinatum), Champagne (Dipteryx odorata), and Peroba do Norte (Goupia glabra Aubl). The results showed the great potential of FTIR and multivariate analysis for wood sample classification; here, the Linear SVM differentiated the five wood species with an accuracy of 98%. The developed method allows industries, laboratories, companies, and control bodies to identify the nature of the wood product after being extracted and semi-manufactured.

Wood-species identification based on terahertz spectral data augmentation and pseudo-label guided deep clustering

ABSTRACT In order to address the problem that existing methods combining spectral data and machine learning for wood species identification rely on labeled samples, this study introduces unsupervised learning into the field of wood identification. It proposes a novel wood-identification model called DCVAE (deep conditional variational autoencoder)-PLCAE (pseudo-label convolutional autoencoders). Terahertz time-domain spectra of wood samples at breast height of five broadleaf and five coniferous species were obtained (40 samples of each species of wood, 400 in total). A conditional variational autoencoder was applied to augment the terahertz spectroscopy dataset. Subsequently, a pseudo-label-guided deep clustering model was developed to extract more discriminative deep features. The model was compared with three traditional clustering algorithms and four deep clustering methods. Clustering experiments and visualization results show that the comprehensive clustering performance of DCVAE-PLCAE is better than the other comparative algorithms and that the extracted low-dimensional features has a more straightforward structure. The algorithm in this study can solve the problems of fewer labeled samples and the difficulty of extracting discriminative features by traditional clustering algorithms.

A deep learning multimodal fusion framework for wood species identification using near-infrared spectroscopy GADF and RGB image

Abstract 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.

Identification of tropical wood species in paper: a new chemotaxonomic method based on extractives

Abstract The European Deforestation Regulation 2023/1115 (EUDR) prohibits trading of wood and wood products obtained from illegal logging on the EU market. While the identification of solid wood via anatomy, chemistry and genetics has already been established, there is a lack of identification methods for pulp and paper that complement anatomy. This publication presents a newly developed chemotaxonomic method for identifying mixed tropical hardwood (MTH) species in pulp and paper products based on their extractives analyzed with thermal desorption-gas chromatography-mass spectrometry (TD-GC-MS). The measured data was processed and compared to identify marker substances and was then merged into a fingerprint database for identifying MTH species in paper of unknown composition. As database references, fully bleached kraft pulps were produced from 38 anatomically identified wood samples and then cryo-ball milled and extracted successively with n-hexane and acetone. The results show that the remaining wood extractives generated from bleached pulps are specific enough to find chemical relevant marker substances to detect MTH species. As chemical composition and anatomy are independent characteristics of wood, this paper makes a completely independent method available, which potentially improves the screening for Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES) protected species.

Timber Structures of Florence Cathedral: Wood Species Identification, Technological Implications and Their Forest Origin

The Cathedral of Florence is one of the largest churches in the world and is known for one of the most famous domes ever, which characterizes the skyline of the city. The dimensions of the building mean that the dimensions of the roof are equally large and so are the wooden structures that support it. The roof of the cathedral is organized on two levels: the roof of the large central nave and, at a lower level, those of the two lateral naves. The purpose of this paper is the identification of the wood species of which the structures are made. The sampling method of the 408 samples that have been identified is then described, the methods followed to reach a reliable identification and finally the results. The timbers most represented among the structural elements are those of silver fir, chestnut and elm. Other timbers are then found in the other components less directly linked to the main structural parts that make up the trusses. The paper then discusses the technological implications on the use of those woods within the wooden covering structures of the cathedral and the main sources of timber that the builders had available, in particular the Casentino forests that the Municipality of Florence had donated to the structure that managed the construction of the cathedral (Opera di Santa Maria del Fiore—OPA). OPA still exists today and is responsible for the maintenance of the cathedral and other annexed buildings.

Genetic Species Identification Using ycf1b, rbcL, and trnH-psbA in the Genus Pinus as a Complementary Method for Anatomical Wood Species Identification

This study proposes the use of genetic analysis as a complementary method for species identification in the genus Pinus, particularly in cases where anatomical identification is challenging. Pinus species were grouped based on anatomical similarities, and the efficacy of using ycf1b, which is the most variable for Pinus species identification, and rbcL, which is a suggested DNA barcode for land plants, was evaluated within each group. Sequences for each species were obtained from the National Center for Biotechnology Information database and were used to perform phylogenetic analysis. Among the species in Group 1 (P. echinata, P. elliottii, P. ponderosa, P. radiata, P. rigida, P. taeda, and P. virginiana), rbcL was only effective in identifying P. radiata and P. ponderosa, while ycf1b classified five species. An additional DNA barcode, trnH-psbA, was needed to identify P. radiata and P. taeda. In Group 2 (P. densiflora, P. sylvestris, and P. thunbergii), most species were identified using both rbcL and ycf1b, with the exception of possible hybrids of P. densiflora and P. sylvestris. In Group 3 (P. koraiensis and P. strobus), two species were identified using rbcL and ycf1b. Combining genetic species identification with anatomical identification can accurately identify species of the genus Pinus.

Building machine learning models to identify wood species based on near-infrared spectroscopy

Abstract Efficient and nondestructive technology for identifying wood species facilitates the transition from digital forestry to smart forestry. While near-infrared spectroscopy applied to wood identification is well documented, the detailed mechanisms for chemometrics remain unclear. In this study, twelve wood species were identified by using near-infrared spectroscopy combined with six machine learning algorithms (support vector machine, logistic regression, naïve Bayes, k-nearest neighbors, random forest, and artificial neural network). Above all, isolated forest and local outlier factor were used to detect and exclude outliers. Then feature engineering strategies were developed from three perspectives to process feature matrices: feature selection, feature extraction, and feature selection combined with feature extraction. Next, the learning curve, grid search method, and K-fold cross-validation were used to optimize the model parameters. Finally, the accuracy, operation time, and confusion matrix were used to evaluate the model performance. When the local outlier factor was used to remove outliers and principal component analysis was used to extract features, the support-vector-machine-based wood-species identification model produced the most accurate results, with 98.24% accuracy. These results offer new avenues for constructing automatic wood-identification systems.

Comparison of DNA extraction methods on CITES-listed timber species and application in species authentication of commercial products using DNA barcoding

Quality and quantity of DNA extracted from wood is important for molecular identification of wood species, which can serve for conservation of wood species and law enforcement to combat illegal wood trading. Rosewood (Dalbergia and Pterocarpus) and agarwood (Aquilaria) are the most commonly found hardwood in timber seizure incidents. To monitor international trade of timber and commercial wood products and to protect these endangered wood species from further population decline, in this study, we have compared three extraction protocols for DNA extraction from 12 samples of rosewood and agarwood timber logs, and later applied the best DNA extraction protocol on 10 commercial wood products claimed to be rosewood and agarwood. We also demonstrated the applicability of DNA mini-barcoding with multi-loci combination with reference library for identifying the species of timber and commercial wood products. We found that a silica column-based method with guanidine thiocyanate-containing binding buffer served the best in DNA extraction from different parts of wood in all three genera with good quality and quantity. Single barcode region ITS2 or multi-loci combinations including ITS2 barcode region generally provide better discriminatory power for species identification for both rosewood and agarwood. All 10 products were identified to species-level using multi-loci combination. In terms of accuracy in labelling, 80% of them were labelled correctly. Our work has shown the feasibility of extracting good quality of DNA from authentic wood samples and processed wood products and identifying them to species level based on DNA barcoding technology.

Wood identification of Cyclobalanopsis (Endl.) Oerst based on microscopic features and CTGAN-enhanced explainable machine learning models.

Accurate and fast identification of wood at the species level is critical for protecting and conserving tree species resources. The current identification methods are inefficient, costly, and complex. A wood species identification model based on wood anatomy and using the Cyclobalanopsis genus wood cell geometric dataset was proposed. The model was enhanced by the CTGAN deep learning algorithm and used a simulated cell geometric feature dataset. The machine learning models BPNN and SVM were trained respectively for recognition of three Cyclobalanopsis species with simulated vessel cells and simulated wood fiber cells. The SVM model and BPNN model achieved recognition accuracy of 96.4% and 99.6%, respectively, on the real dataset, using the CTGAN-generated vessel dataset. The BPNN model and SVM model achieved recognition accuracy of 75.5% and 77.9% on real dataset, respectively, using the CTGAN-generated wood fiber dataset. The machine learning model trained based on the enhanced cell geometric feature data by CTGAN achieved good recognition of Cyclobalanopsis, with the SVM model having a higher prediction accuracy than BPNN. The machine learning models were interpreted based on LIME to explore how they identify tree species based on wood cell geometric features. This proposed model can be used for efficient and cost-effective identification of wood species in industrial applications.