Identification Of Wood Species Research Articles

Evaluation of Wood Species Identification Using CNN-Based Networks at Different Magnification Levels

Evaluation of Wood Species Identification Using CNN-Based Networks at Different Magnification Levels

King Khufu’s Second Boat: Scientific Identification of Wood Species for Deckhouse, Canopy, and Forecastle

Very little published information is available on the scientific identification of wood species used in the construction of boats in ancient Egypt. This paper deals with the scientific identification of wood species used in the construction of the deckhouse, canopy, and forecastle of King Khufu’s second wooden boat (4th Dynasty—Old Kingdom) in detail. This paper also discusses the principal technological characteristics of the identified woods, considering specifically their utilization for construction of the deckhouse, canopy, and forecastle. Almost all the woods used in the boat’s deckhouse, canopy, and forecastle were made of two imported species of wood (Cedrus libani A.Rich. and Juniperus sp.), with two native species (Ziziphus spina-christi (L.) Willd. and Vachellia sp.) also identified. The analysis most surprisingly revealed the presence of Ziziphus spina-christi (L.) Willd. in 25% of the analyzed forecastle samples, which was discovered for the first time for making cross beams in the construction of boats in ancient Egypt. Another intriguing aspect of the boat’s construction is the presence of Juniperus sp., which surprisingly showed that almost 85% of the analyzed samples were Juniperus sp., used in the deckhouse’s boards, frames, and cross beams. The data let us examine the specific employment of the wood species used in the parts of the boat, which evidenced that the identified woods were suitably used for the construction of the different parts of the deckhouse, canopy, and forecastle of the boat.

Scope of Wood Scanning Applications in India - A Review

This article describes the opportunities of major wood scanning technologies in the Indian forestry field. Researchers have developed various non-destructive technologies to better understand the inner properties of wood. In the wood industry, the correct identification of wood species and their physical (in furniture industries) and chemical (in paper and pulp industries) characteristics is critical for end-use applications. The measurements of wood properties (Elastic properties, Thermal properties, Electrical properties, Dielectric properties, and Ionization radiation properties) with the help of wood scanning technologies are used for locating and quantifying wood decay and knots in both standing trees and logs. These measurements have been employed in various perspectives on forestry applications. For instance, measurement of Modulus of Elasticity (MoE) is used to assess thinning effects and tree health assessments, and as a breeding criterion in tree improvement. This article aims to describe major wood scanning technologies that provide tomography of wood and the scope of wood scanning technologies, and their current status in the Indian forestry field. The major wood scanning technologies include Acoustic Tomography, Electrical Impedance Tomography, Magnetic Induction Tomography, Radiography Computed Tomography, and Microwave Tomography.

Machine Learning-Based Species Classification Methods Using DART-TOF-MS Data for Five Coniferous Wood Species

Various problems worldwide are caused by illegal production and distribution of timber, such as deception about timber species and origin and illegal logging. Numerous studies on wood tracking are being conducted around the world to demonstrate the legitimacy of timber. Tree species identification is the most basic element of wood tracking research because the quality of wood varies greatly from species to species and is consistent with the botanical origin of commercially distributed wood. Although many recent studies have combined machine learning-based classification methods with various analytical methods to identify tree species, it is unclear which classification model is most effective. The purpose of this work is to examine and compare the performance of three supervised machine learning classification models, support vector machine (SVM), random forest (RF), and artificial neural network (ANN), in identifying five conifer species and propose an optimal model. Using direct analysis in real-time ionization combined with time-of-flight mass spectrometry (DART-TOF-MS), metabolic fingerprints of 250 individual specimens representing five species were collected three times. When the machine learning models were applied to classify the wood species, ANN outperformed SVM and RF. All three models showed 100% prediction accuracy for genus classification. For species classification, the ANN model had the highest prediction accuracy of 98.22%. The RF model had an accuracy of 94.22%, and the SVM had the lowest accuracy of 92.89%. These findings demonstrate the practicality of authenticating wood species by combining DART-TOF-MS with machine learning, and they indicate that ANN is the best model for wood species identification.

Identification of softwood species using convolutional neural networks and raw near-infrared spectroscopy

ABSTRACT Previous reports have shown that wood species identification result based on near-infrared (NIR) spectroscopy was intimately entwined with spectra preprocessing. However, there is no universal recipes for a suitable preprocessing method, and misuse of preprocessing may bring on worse model performance for new species identification. Therefore, a convolutional neural network (CNN) model incorporating a residual connection structure is created aiming at replacing the preprocessing and identifying 21 Pinaceae species at the species level. The model is compared to the other two CNN models on different wavelength range raw transverse section NIR spectra. 12 preprocessing methods are carried out for 780–2440 nm spectra to evaluate the influence of spectra preprocessing on the model. The model outperforms the other two CNN models on raw and preprocessed spectra and provides the highest macro F1 of 0.9787 and 0.9792 for raw and preprocessed spectra at the wavelength range of 780–2440 nm. The model is further compared to three conventional methods. The results indicated that created model is capable to replace the spectra preprocessing and identify 21 wood species at the species level. It is indicated that a suitable CNN structure can replace the multifarious data preprocessing in traditional methods. It potentially provides a generic raw NIR spectra discrimination method for wood species identification.

Identification of wood species and duration of exposure in weathered wood using guided wave propagation

ABSTRACT Nondestructive health monitoring of weathered timber structures in outdoor applications is a critical safety and quality control task. This study proposes a guided Lamb wave propagation approach for identifying the type of wood and estimating the duration of exposure in different wood species under artificial weathering. Accordingly, alder, fir, oak, and poplar wood specimens underwent accelerated weathering conditions. The intact and degraded wood specimens were assessed via the Lamb wave propagation experiments, and different sensory features were extracted and used to train machine learning models. The decision tree and random forest classification were performed to identify the type of wood and the duration of exposure to weathering. The results of the decision tree classification indicated that the extracted wave-based features could identify the type of wood species with an accuracy of 82.5%. The wave features could also classify the duration of exposure to weathering with a maximum accuracy of 75%. Higher classification performance was obtained using the random forest model where the wood species and exposure duration were classified with an accuracy of 85% and 81.25%, respectively. Overall, the guided Lamb wave propagation exhibited the potential for in-situ assessment and species identification of weathered wood in outdoor conditions.

Similarity network fusion for aggregating headspace GC–MS and direct analysis in real time–mass spectrometry data from solid samples to enhance species identification efficiency of high–temperature heated wood

Pterocarpus santalinus and Pterocarpus tinctorius are commonly used species of the genus Pterocarpus in the wood trade. Although both of them have been listed in Appendix II of the Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES) since 2019, it is still critical to identify them in terms of plant taxonomy. Currently, high-temperature heating is an accepted treatment method for high-density wood species such as Pterocarpus to improve dimensional stability and restore previous drying defects partially. It has proved challenging to identify the high-temperature (e.g., 120 °C) heated wood from these two species. Thus, this study approaches species identification of two Pterocarpus of high-temperature (e.g., 120 °C) heated solid wood samples using headspace–gas chromatography–mass spectrometry (HS–GC–MS). Besides, a computational analytical method named similarity network fusion (SNF) was proposed to aggregate data in two different types, respectively, derived from the HS–GC–MS and direct analysis in real time–mass spectrometry (DART–MS) to explore the feasibility of improving the efficiency and accuracy of wood species discrimination. The SNF exhibits more significant differences and higher predictive accuracy (100%) between P. santalinus and P. tinctorius than that based on the HS–GC–MS data (77.78%) or DART–MS (66.67%) alone. These results demonstrated the capability of the HS–GC–MS technique in the analysis of high-temperature heated solid wood and the potential of multidimensional or comprehensive data sets based on the SNF algorithm in the field of wood species identification.

Improved wood species identification based on multi-view imagery of the three anatomical planes

BackgroundThe identification of tropical African wood species based on microscopic imagery is a challenging problem due to the heterogeneous nature of the composition of wood combined with the vast number of candidate species. Image classification methods that rely on machine learning can facilitate this identification, provided that sufficient training material is available. Despite the fact that the three main anatomical sections contain information that is relevant for species identification, current methods only rely on transverse sections. Additionally, commonly used procedures for evaluating the performance of these methods neglect the fact that multiple images often originate from the same tree, leading to an overly optimistic estimate of the performance.ResultsWe introduce a new image dataset containing microscopic images of the three main anatomical sections of 77 Congolese wood species. A dedicated multi-view image classification method is developed and obtains an accuracy (computed using the naive but common approach) of 95%, outperforming the single-view methods by a large margin. An in-depth analysis shows that naive accuracy estimates can lead to a dramatic over-prediction, of up to 60%, of the accuracy.ConclusionsAdditional images from non-transverse sections can boost the performance of machine-learning-based wood species identification methods. Additionally, care should be taken when evaluating the performance of machine-learning-based wood species identification methods to avoid an overestimation of the performance.

An algorithmic method for the identification of wood species and the classification of post-consumer wood using fluorescence lifetime imaging microscopy

Abstract. In this contribution the frequency domain fluorescence lifetime imaging microscopy (FD-FLIM) technique is evaluated for post-consumer wood sorting. The fluorescence characteristics of several wood samples were determined, whereby two excitation wavelengths (405 and 488 nm) were used. The measured data were processed using algorithmic methods to identify the wood species and post-consumer wood category. With the excitation wavelength of 405 nm, 16 out of 19 samples could be correctly assigned to the corresponding post-consumer wood category by means of the fluorescence lifetimes. Thus, the experimental results revealed the high potential of the FD-FLIM technique for automated post-consumer wood sorting.

Wood species recognition from wood images with an improved CNN1

With the development of convolutional neural networks, aiming at the problem of low efficiency and low accuracy in the process of wood species recognition, a recognition method using an improved convolutional neural network is proposed in this article. First, a large-scale wood dataset was constructed based on the WOOD-AUTH dataset and the data collected. Then, a new model named W_IMCNN was constructed based on Inception and mobilenetV3 networks for wood species identification. Experimental results showed that compared with other models, the proposed model had better recognition performance, such as shorter training time and higher recognition accuracy. In the data set constructed by us, the accuracy of the test set reaches 96.4%. We used WOOD-AUTH dataset to evaluate the model, and the recognition accuracy reached 98.8%. Compared with state-of-the-art methods, the effectiveness of the W_IMCNN were confirmed.

An effective and fast solution for classification of wood species: A deep transfer learning approach

Classification and recognition of wood species have critical importance in wood trade, industry, and science. Therefore, accurate identification of wood species is a great necessity. Conventional classification and recognition of wood species require knowledge and experience on the anatomy of wood which is time-consuming, cost-ineffective, and destructive. Hence, convolutional neural networks (CNNs) -a deep learning tool- have replaced the conventional methods. In this study, classification of wood species via the WOOD-AUTH dataset and evaluating the performance of various deep learning architectures including ResNet-50, Inception V3, Xception, and VGG19 in classification with transfer learning was investigated in detail. The dataset contains macroscopic images of 12 wood species with three different types of wood sections: cross, radial and tangential. The experimental findings demonstrate that Xception produced a remarkable performance as compared to the other models in this study and the WOOD-AUTH dataset owners, yielding a classification accuracy of 95.88%.

The Relationship between Carving Work and Timber Features: A Database for the Italian Wooden Statuary

Wood has a wide range of applications in the artistic field, most of the time used as a support for works of art, for example, in panel paintings. Compared with stones and metals, wood is by far the material most utilised for sculptures. Through the identification of wood species, a study of timbers used in statuary in Europe, with a deeper exploration of the works of art preserved in Italy, can provide further insights for historical–artistic studies. Indeed, in reality, generic wood does not exist, but there are different timbers. This is a notion that the wood fine carving artists/craftsmen knew well. The initial idea of this study was to verify whether timber features could influence the formal results in figurative carving; therefore, a specific database that had been developed to catalogue the carving works was used for which the identification of wood species was carried out through reliable methodologies. The aim of this research was to analyse the relationship between the timber species used in statuary, the formal results of carving, and the thickness of the preparatory layer, through the data stored in a specific database, called ArISStArt. It contains a sort of registry of artistic carving and inlay works: For each artefact, a record was compiled consisting of different fields, which contains the historical–artistic information available, including the images of the artefact and also types of timber/s used for its creation, with a link to the relative field. The number of the recorded artefacts is, at present, 480. On most of the artefacts, more than one sample was taken; therefore, the total number of identifications carried out corresponds to 691. Based on the results, the vast majority of wooden statuary is carved from hardwoods, more specifically hardwoods, with diffuse porosity and small variations in density within the growth ring. The timber most present is poplar, followed by lime and walnut. With the listed three timbers, almost 80% of the artefacts recorded in ArISStArt were created.

Nondestructive identification of wood species by terahertz spectrum

AbstractTerahertz time‐domain spectroscopy (THz‐TDS) has become an emerging nondestructive detection technique due to the unique properties of THz waves; it offers safety, penetrability, and fingerprint identification, especially for commonly used non‐polar materials. Here, we measure the differences in THz spectra of four wood blocks (manglietia, amur linden, black walnut, and ebony) in the frequency range of 0.1–0.9 THz. In addition, we demonstrate the principal components analysis (PCA) applied in THz absorption spectra; the principal components extracted from original data by PCA can replace the original absorption coefficient data and can clearly distinguish the wood types. Results show that THz‐TDS combined with PCA can be used as an effective nondestructive identification method in the field of public security, food detection, and customs anti‐smuggling initiatives.

X-ray Tomography Unveils the Construction Technique of Un-Montu's Egyptian Coffin (Early 26th Dynasty).

The Bologna Archaeological Museum, in cooperation with prestigious Italian universities, institutions, and independent scholars, recently began a vast investigation programme on a group of Egyptian coffins of Theban provenance dating to the first millennium BC, primarily the 25th–26th Dynasty (c. 746–525 BC). Herein, we present the results of the multidisciplinary investigation carried out on one of these coffins before its restoration intervention: the anthropoid wooden coffin of Un-Montu (Inv. MCABo EG1960). The integration of radiocarbon dating, wood species identification, and CT imaging enabled a deep understanding of the coffin’s wooden structure. In particular, we discuss the results of the tomographic investigation performed in situ. The use of a transportable X-ray facility largely reduced the risks associated with the transfer of the large object (1.80 cm tall) out of the museum without compromising image quality. Thanks to the 3D tomographic imaging, the coffin revealed the secrets of its construction technique, from the rational use of wood to the employment of canvas (incamottatura), from the use of dowels to the assembly procedure.

Microscopic identification of brazilian commercial wood species via machine-learning

Background: Multiple challenges are faced by industry and certification agencies when commercializing tropical species. Anatomical similarities of tropical hardwoods impair identification. Deep learning models can facilitate microscopic identification of wood by using sophisticated techniques such as deep convolutional networks (DCNN). Our objective was to microscopically identify 23 commercially available Brazilian wood species using a custom DCNN model. Results: Photographs from microscopic slides of each wood species were processed, and the final data set contained 2,448 images. We applied stratified k-fold cross-validation technique during training to increase model’s robustness and trustworthiness. Thus, the dataset was divided into approximately 80% training (1,958 images) and 20% validation (490 images) for each fold. A series of augmentations were performed only on training data to include variations in rotation, zoom, and perspective. Image augmentation was performed on-the-fly. The network consisted of convolutions, max pooling, global average pooling, and fully connected layers. We tested the performance of the DCNN against accuracy, precision, recall, and F1-score on the validation set for each fold. Conclusion: The custom machine learned model accuracy was higher than 0.90. The model’s worst performance was identified in distinguishing between Toona ciliate and Khaya ivorensis, which was due more to wood variability than to a machine learning deficiency. Future studies should focus on integration, verification/monitoring, and updating of current models for end user manipulation, trust, ethics, and security.

The Yew Cross from Szczuczyn – a Symbol of Life and Death or an Unusual Memento?

Archaeological research in the crypts of the Church of the Holy Name of the Virgin Mary in Szczuczyn has been carried out since 2012. Many years of research have made it possible to identify some of the buried people, including the Piarists who served as the hosts of the church. One of the monks identified was Stanislaw Marszycki, who took the name Simeon of St Joseph after his monastic vows. Identification of the Piarist was possible thanks to the information on the coffin. On the deceased’s vestments rested a wooden crucifix, which can be interpreted as part of the deceased’s individual equipment. The crucifix was subjected to wood species identification using a microscope with transmitted light. This made it possible to determine that it was made from the wood of the common yew tree (Taxus baccata L.). Yew wood is a valuable material and was used to make both large boatbuilding components, furniture, and weapons, and was also readily used in 18th- -century gardens. The yew was also a tree around which there was a great deal of superstition. Because of its toxicity and longevity, it was treated as both a tree of death and life. The cross from the monk’s coffin, according to superstition, might have guarded the deceased against evil, been an individual object with which the deceased was associated, or perhaps was chosen because yew wood was eminently polishable and with a beautiful colouration.

Efficiency of preprocessing methods for discrimination of anatomically similar pine species by NIR spectroscopy

ABSTRACT Identification of wood species with fast, reliable and non-destructive methods is highly important for forestry and wood-related industries. Near-infrared spectra of anatomically similar pine species (Pinus sylvestris L. and Pinus nigra J.F. Arnold) were taken and analysed by partial least squared discriminant analysis (PLS-DA) for comparing the efficiency of preprocessing methods. Raw data were subjected to multiple scatter correction (MSC), standard normal variate (SNV), Savitzky–Golay for derivatives (1st and 2nd Dr) and smoothing (Sm) and combination of these preprocessing methods (1st Dr, 1st Dr + SNV, 1st Dr + MSC, Sm + 1st Dr and Sm + 2nd Dr). The success of the models was determined by the accuracies of test sets that did not participate in the calibration phase. In this study, it was determined that not all the preprocessing methods improve the model performance. Smoothing with 1st derivatives (Sm + 1st Dr) enhanced 14.3% improvement and have the best performance (95%) for classification of pine species. For understanding modelled relationship, mean spectra and selectivity ratio were used. It was found that discrimination was held by the differences at their absorption, and the most important variables for wood classification were noted around 4000–7000 cm−1.

Analysis of Anatomical Characteristics for Wood Species Identification of Commercial Plywood in Korea

International efforts to prevent illegally logged wood are expanding around the world. The “Legal Wood Trade Promotion System” was enacted in Korea in 2019 to strengthen the legal import and distribution of commercial wood in Korea. Since then, this system has promoted and ensured that the imported wood and wood products are legal with respect to the country of origin, wood species, and harvested area. As verification methods, DNA analysis technology and anatomical analysis using a microscope are mainly used in conjunction. Therefore, in this study, wood species of plywood were identified by analyzing the anatomical characteristics of various wood products for the first time. Douglas fir (Pseudotsuga menziesii (Mirb.) Franco.) and larch (Larix kaempferi (Lamb.) Carriere) plywoods (7, 9 ply) were obtained from four companies that supply plywood in Korea. After cutting each company

Transport of Timber – A Matter of Ancient Concern: New Results on Prehistoric Transport of Timber by Means of Anatomical Wood Species Identification

Transport of Timber – A Matter of Ancient Concern: New Results on Prehistoric Transport of Timber by Means of Anatomical Wood Species Identification

Rapid identification of wood species using XRF and neural network machine learning

An innovative approach for the rapid identification of wood species is presented. By combining X-ray fluorescence spectrometry with convolutional neural network machine learning, 48 different wood specimens were clearly differentiated and identified with a 99% accuracy. Wood species identification is imperative to assess illegally logged and transported lumber. Alternative options for identification can be time consuming and require some level of sampling. This non-invasive technique offers a viable, cost-effective alternative to rapidly and accurately identify timber in efforts to support environmental protection laws and regulations.