Wood Recognition Research Articles

Prior knowledge-based DMV model for few-shot and multi-category wood recognition

Prior knowledge-based DMV model for few-shot and multi-category wood recognition

Improved plant parenchyma extraction technology using artificial intelligence algorithms

The previous studies have described the extraction of plant parenchyma by computer image processing technology, and the purpose of this paper is to verify the effectiveness of the algorithm., this paper implements the algorithm by using Matlab language, and designs several groups of experiments. The experimental results show that: when denoising, using 9*9 as a template to perform median filtering on the image has a better effect, and block binarization facilitates the extraction of axial parenchyma; when processing mathematical morphology, using 3*3 Axial parenchyma and vessel morphology can be successfully extracted from cross-sectional images of broad-leaved wood after dilation of the image by cross-shaped structuring elements and erosion of images by disc-shaped structuring elements with radii ranging from 1 to 10 When calculating the area threshold of the closed area, the area threshold is determined by using 8 domains to mark the area of the closed area and using the area histogram, so that the axial parenchyma can be better separated from the catheter. At present, the method has been experimented in 10 different tree species, all of which have achieved good results. This also fully proves the effectiveness of the artificial intelligence algorithm. The implementation of the algorithm also lays the foundation for future research on intelligent wood recognition based on axial thin-walled tissue morphology; it provides a shortcut to measure the content of axial thin-walled tissue in different tree species; and it is a prelude to the development of an image-based wood recognition system for axial thin-walled tissue.

Indonesian Commercial Woods Classification Based on GLCM and K-Nearest Neighbor

Currently, the presence of wood is becoming increasingly scarce. In addition, the recognition of wood is still using wood experts, who basing their judgments on the characteristics that can be seen by eye directly such as color, texture and so on. However, wood experts are still few and have a disadvantage that the results obtained are still not sufficiently accurate and time consuming. The purpose of this research is to develop Indonesian commercial woods classification system based on GLCM and k-Nearest Neighbor. Procedures of the wood classification system includes image acquisition using a digital camera, then a preprocessing steps by converting the original image to grayscale image and sharpening the image, after that do texture feature extraction using Gray Level Cooccurrence Matrix (GLCM) with the parameters used are Contrast, Correlation , Energy, Entropy, and Homogeneity, at each direction that are 0°, 45°, 90°, 135°,and the last step is the classification using the k-Nearest Neighbor (k-NN). The testing results show that the testing data can be classified accurately 100% is a testing data derived from the training database with k = 1. In general, the greater the value of k then the classification success rate decreases.

An Improved Wood Recognition Method Based on the One-Class Algorithm

Wood recognition is necessary for work in the wood trade activities. The advantage of the one-class wood classification method is more generalization, and it only needs positive samples and does not need negative samples in the training phase, so it is suitable for rare wood species inspection. This paper proposed an improved method based on the one-class support vector machine (OCSVM) for wood species recognition. It uses cross-section images acquired with a magnifying glass, which uses a pre-trained VGG16 model for feature extraction, a normal distribution test for key features filtering, and OCSVM to determine the wood species. The results showed that the approach achieved a mean recall of 0.842 for both positive and negative samples, which indicates this method has good performance for wood recognition. In a negative public dataset, the negative recall reached as high as 0.989, which showed that this method has good generalization.

The applications of machine vision in raw material and production of wood products

Machine vision has been developed nearly for 70 years and been widely applied in electronics, automotive manufacturing, food processing, etc. With deepening study of its theory and technology in forestry industry, the industry of wood products is moving steadily toward the goal of automated identification and production to improve the manufacturing intelligence of enterprises. In this study, theoretical and algorithmic research on image acquisition, feature extraction, recognition, and classification involved in machine vision-based wood recognition technology were analyzed on the basis of its global development. The applications of machine vision in the wood materials, such as the identification of tree species, wood inspection and classification, defects detection of wood product, surface analysis of wood color, and quality control of furnishing products were thoroughly analyzed. The development trend of machine vision in the production and management of wood materials was considered in the current development of wood and furnishing enterprises. These results lay a solid foundation for wood science research, and intelligent manufacture of wooden furniture, and efficient development of greener and cleaner production of the furniture industry, which could improve the environmental effect of the wood products and furniture and make a great contribution for the carbon goal of “30-60” in China.

Damage Modes Recognition of Wood Based on Acoustic Emission Technique and Hilbert–Huang Transform Analysis

Identifying the different damage modes of wood is of great significance for monitoring the occurrence, development, and evolution of wood material damage. This paper presents the research results of the application of acoustic emission (AE) technology to analyze and evaluate the mapping relationship between the damage pattern of wood in the fracture process and the AE signal. For the three-point bending specimen with pre-crack, the double cantilever beam specimen, the single fiber tensile specimen, and the uniaxial compression specimen, the bending tensile compression test and the AE monitoring were performed, respectively. After the post-processing and analysis of the recorded AE signal, the results show that the peak frequency of AE is an effective parameter for identifying different damage modes of wood. In this study, the empirical mode decomposition (EMD) of the AE signal can separate and extract a variety of damage modes contained in the AE signal. The Hilbert–Huang transform (HHT) of the AE signal can clearly describe the frequency distribution of intrinsic mode function (IMF) components in different damage stages on the time scale, and can calculate instantaneous energy accurately, which provides a basis for damage mode recognition and lays a foundation for further accurate evaluation of the wood damage process.

Geometric and Topological Bases of a New Classification of Wood Vascular Tissues, Part 2: Classification of Vessels According to Their Grouping

The arrangement of vessels and their grouping is unique in most tree species. When observing tiny, microscopic samples of wood, the arrangement of the wood vessels forms a characteristic and repetitive pattern, which is largely determined by the tree species, but it is also influenced by the site conditions as well as its location in the tree. The present study is part of a project aimed at applying computer vision and computer recognition methods to present a more general and comprehensive group classification of wood vessels. Quantitative descriptions of the grouping of vessels, as a rule, have so far been used mainly to reveal characteristic deviations from the typical structure of wood, for example, due to extreme site conditions. Therefore, they are applicable but not sufficient for the present study and need in-depth revision. A classification of vessels is presented depending on their mutual position, and more precisely, the groups of adjacent vessels are determined using quantitative methods. The quantitative indicators used for this purpose are based on the diameter and other quantitative indicators of the vessels’ arrangements. The proposed classification, although based on a long-known classification scheme in structural wood science, allows for the more precise definition of the classes of a grouping of adjacent vessels in a cross-section as a necessary step towards the wider use of the methods of machine recognition of wood.

Pengenalan Jenis Kayu Berdasarkan Citra Makroskopik Menggunakan Metode Convolutional Neural Network

Until now, wood has an irreplaceable function. Building materials, shipping, furniture, sports equipment, carvings and handicrafts using wood. Indonesia has more than 4,000 types of wood, so choosing the right wood is a challenge because choosing the wrong type of wood can make the quality of processed products decline and not as expected. In addition, proper identification of timber can also prevent illegal logging, especially on certain types of wood which are now increasingly scarce. Recognition to wood by looking directly is a difficult thing for ordinary people to do and can only be done by a wood expert, so it is necessary to find a method of recognizing wood that can be used by people independently. One method that can be used to identify type of wood is image processing based on characteristics of wood which include color, fiber direction and texture. This paper will describe recognition of wood-based image processing using Convolutional Neural Network (CNN) method. This method is derived from Neural Networks with addition of an extraction layer feature, which can reduce free parameters that are not needed by the system. Wood image data used in this study are four types of wood that are often used as raw materials for making houses and furniture, namely Glugu, Teak, Sengon and Waru. Results of this study were able to recognize four types of wood with an accuracy of 95% in 600 epochs/iteration, so that it can be used as a simple, easy and inexpensive wood recognition system.

Evaluation of image partitioning strategies for preserving spatial information of cross-sectional micrographs in automated wood recognition of Fagaceae

Although wood cross sections contain spatiotemporal information regarding tree growth, computer vision-based wood identification studies have traditionally favored disordered image representations that do not take such information into account. This paper describes image partitioning strategies that preserve the spatial information of wood cross-sectional images. Three partitioning strategies are designed, namely grid partitioning based on spatial pyramid matching and its variants, radial and tangential partitioning, and their recognition performance is evaluated for the Fagaceae micrograph dataset. The grid and radial partitioning strategies achieve better recognition performance than the bag-of-features model that constitutes their underlying framework. Radial partitioning, which is a strategy for preserving spatial information from pith to bark, further improves the performance, especially for radial-porous species. The Pearson correlation and autocorrelation coefficients produced from radially partitioned sub-images have the potential to be used as auxiliaries in the construction of multi-feature datasets. The contribution of image partitioning strategies is found to be limited to species recognition and is unremarkable at the genus level.

Application of variant transfer learning in wood recognition

Wood is a material commonly found in nature and is widely used in all professions and industries. Because wood has varied growth cycles and physical properties, there are large differences in its usage and commercial price. In addition, some woods are nationally protected species. Therefore, it is of great importance to accurately identify the type of wood. Traditional wood recognition methods rely on experts and specialized equipment. To facilitate wood recognition, this paper proposes an approach for wood recognition using images. Next, a transfer learning technology was used to extract the textural features of wood, and a global average pooling (GAP) layer was used to reduce the number of features. Finally, the extreme learning machine (ELM) was used for classification. The recognition accuracy of this approach for the Wood Species Dataset was 93.07%, which was higher than the method used by the data provider. This approach had a higher recognition accuracy and a more stable recognition performance than previous approaches.

Wood Recognition and Quality Imaging Inspection Systems

Forestry is an undoubtedly crucial part of today’s industry; thus, automation of certain visual tasks could lead to a significant increase in productivity and reduction of labor costs. Eye fatigue or lack of attention during manual visual inspections can lead to falsely categorized wood, thus leading to major loss of earnings. These mistakes could be eliminated using automated vision inspection systems. This article focuses on the comparison of researched methodologies related to wood type classification and wood defect detection/identification; hence, readers with an intention of building a similar vision-based system have summarized review to build upon.

Online System for Automatic Tropical Wood Recognition

There are more than 3000 wood species in tropical rainforests, each with their own unique wood anatomy that can be observed using naked eyes aided with a hand glass magnifier for species identification process. However, the number of certified personnel that have this acquired skills are limited due to lenghty training time. To overcome this problem, Center for Artificial Intelligence & Robotics (CAIRO) has developed an automatic wood recognition system known as KenalKayu that can recognize tropical wood species in less than a second, eliminating laborious manual human inspection which is exposed to human error and biasedness. KenalKayu integrates image acquisition, feature extraction, classifier and machine vision hardware such as camera, interfaces, PC and lighting. Grey level co-occurrence matrix (GLCM) is used for feature extraction. The features are trained in a back-propagation neural network (BPNN) for classification. This paper focusses more on the database development and the online testing of the wood recognition system. The accuracy of the online system is tested on different image quality such as image taken in low light condition, medium light condition or high light condition.

Application of image quality assessment module to motion-blurred wood images for wood species identification system

Despite tighter conservation regulations, demand for timber products has continued to increase due to growing population. Normally, experts identify the wood species based on the pattern of the wood surface texture. However, manual inspection on wood texture is tedious, time-consuming, impractical and cost-ineffective for a human to analyze a large number of timber species. Therefore, a reliable automatic wood recognition system is needed in order to classify the wood species efficiently. The proposed system includes image acquisition, image quality assessment module (IQA), image deblurring, feature extraction and classification. In this research, the wood images are motion-blurred due to imperfections in the imaging and capturing process. Hence, an IQA module is proposed to monitor the quality of images before proceeding to the next stage which is the feature extraction process. The IQA module will determine whether the image has to undergo the image deblurring process based on the image quality value. If the image is of low quality based on the image quality value obtained, then the image will be deblurred before the feature extraction procedure. A reliable motion deblurring technique, which is based on Lucy–Richardson algorithm, is employed to enhance the motion-blurred images before proceeding to the next stage, which is the feature extraction process. Then, a statistical feature extraction technique is proposed to extract 24 features from each wood image. Finally, a support vector machine is used to classify the 20 tropical wood species.

Wood species identification using terahertz time-domain spectroscopy

A new method for wood identification using terahertz (THz) time-domain spectroscopy (TDS) is presented. THz-TDS technology is an emerging method of spectral analysis method that shows great advantages in wood non-destructive testing. Wood is opaque in the optical and near infrared spectrum, and relatively transparent in the THz band. In this experiment, four wood species (Pinus densiflora, Pinus sylvestris, Pseudotsuga menziesii, and Cunninghamia lanceolata) were selected as samples. Optical parameters such as absorption coefficient and refractive index of the measured samples can be extracted from THz time-domain spectra. Principal component analysis was introduced to reduce the dimensionality of the THz spectral data of the wood. The principal component score matrix of the wood was obtained and used as a characteristic matrix. A wood classification model was established using a support vector machine. The experimental results showed that THz-TDS had excellent performance in wood recognition. This research lays a theoretical and application foundation for the application of THz technology in the field of wood detection and recognition. It also provides a new direction and technical scheme in the wood identification field.

Denoising module for wood texture images

The need for an effective automatic wood species identification system is becoming critical in the timber industry with the intention to sustain and improve productivity and quality of the timber products in furniture industry and housing industry. The first stage in an automatic wood recognition system is the image acquisition process where wood images are captured and stored in the database. Good quality wood images must be obtained during the acquisition process in order to guarantee effective results. One of the main issues in identifying wood species effectively is the blurred images of wood texture captured during the image acquisition process. To cater the above-mentioned problem, wood image denoising process is crucial for the timber industry. An image denoising module is proposed to improve the image representation of the wood texture by using the expectation–maximization (EM) adaption algorithm. Then, image quality assessment techniques are applied to evaluate the quality of the denoised wood images. Finally, the performance of the proposed denoising technique is compared to several denoising techniques at various noise levels. In this research, 52 wood species are used where the size of each wood image is 768 × 576 pixels with 256 gray levels at 300 dpi resolution. Experimental results tabulate the mean and standard deviation of the image quality assessment values for each technique at various noise levels. It can be seen that the proposed method EM adaption filter gives the best peak signal-to-noise ratio performance compared to other techniques. In conclusion, the proposed EM adaptation method gives the best performance in denoising the wood texture images at various noise levels compared to other techniques, such as homomorphic filtering, direct inverse filter, Wiener filter, constrained least squares, Lucy–Richardson algorithm, and EM filter.

Discrimination of wood species based on a carbon nanotube/polymer composite chemiresistor array

AbstractFast and efficient alternative methods for wood species identification are needed to combat illegal logging and to control fair trade. One of the possibilities of rapid wood recognition is via chemiresistor gas sensor arrays (“electronic nose”), the application of which is described in the present paper. Carbon nanotube composites (CNTs) of eight insulating polymers were prepared through solution processing and spin casting. The optimum amount of CNTs in the composites was determined by resistance measurement and the CNTs were characterized by scanning electron microscopy. In the case of static headspace analysis, the sensor responses were reproducible and discernible for the wood species. This was demonstrated based on five wood species (Pterocarpus indicus,Acacia auriculiformis,Gmelina arborea,Vitex parvifloraandDiospyros philippinensis). Discrimination of the data was achieved through principal component analysis (PCA) and hierarchical cluster analysis (HCA). PCA score plots and groupings in HCA dendrograms rendered possible the discrimination of these wood species. The potential application of the sensor array approach for wood species identification is high.

Wood species recognition through multidimensional texture analysis

Wood recognition is a crucial task for wood sciences and industries, since it leads to the identification of the anatomical features and physical properties of wood. Traditionally, the recognition process relies almost exclusively on human experts, who are based on various characteristics of wood, such as color, structure and texture. However, there are numerous types of wood species in the nature that are difficult to be identified even by experienced scientists. Towards this end, in this paper we propose a novel approach for automated wood species recognition through multidimensional texture analysis. By taking advantage of the fact that static wood images contain periodic spatially-evolving characteristics, we introduce a new spatial descriptor considering each wood image as a collection of multidimensional signals. More specifically, the proposed methodology enables the representation of wood images as concatenated histograms of higher order linear dynamical systems produced by vertical and horizontal image patches. The final classification of images, i.e., histogram representations, into wood species, is performed using a Support Vector Machines (SVM) classifier. For the evaluation of the proposed method, a dataset, namely “WOOD-AUTH”, consisting of more than 4200 wood images (from cross, radial and tangential sections of normal wood structure) of twelve common wood species existing in Greek territory, was created. Experimental results presented in this paper show the great potential of the proposed methodology, which, despite a small number of misclassification cases with regards to both anatomically similar and different species, outperforms a number of state of the art approaches, yielding a classification rate of 91.47% in wood cross sections.

Frederick J. Swanson’s 1976–1979 papers on the effects of instream wood on fluvial processes and instream wood management

The recognition of instream wood as a key element of river ecosystems and a driver of fluvial processes is now well established, but it did not start until the second half of the twentieth century. A landmark reference work which led to the development of concepts and methods which are still employed in instream wood studies today was the work by Frederick J. Swanson and his papers published between 1976 and 1979. In this article we revisit these papers, highlighting the pioneering observations about the effects of instream wood on fluvial morphology, the description of the instream wood sources and recruitment processes and the discussion about management of wood in rivers. The instream wood research has grown dramatically since the late 1970s, however many knowledge gaps remain; this short historical review illustrates the importance of continuing and developing those research lines into the future.

Wood species identification using spectral reflectance feature and optimal illumination radian design

We developed a novel wood recognition scheme based on wood surface spectral features that aimed to solve three problems. First was elimination of noise in some bands of wood spectral reflection curves. Second was improvement of wood feature selection based on analysis of wood spectral data. The wood spectral band is 350–2500 nm, a 2150D vector with a spectral sampling interval of 1 nm. We developed a feature selection procedure and a filtering procedure by solving the eigenvalues of the dispersion matrix. Third, we optimized the design for the indoor radian’s mounting height. We used a genetic algorithm to solve the optimal radian’s height so that the spectral reflection curves had the best classification information for wood species. Experiments on fivecommon wood species in northeast China showed overall recognition accuracy >95 % at optimal recognition velocity.

Automated recognition of wood used in traditional Japanese sculptures by texture analysis of their low-resolution computed tomography data

The identification of wood species used in the cultural artifacts is important in terms of their preservation and inheritance. However, a nondestructive method is required, and wood samples must be partly cut off in conventional methods such as microscopy. In this study, we constructed a novel system for wood identification using image recognition of X-ray computed tomography images of eight major species used in Japanese wooden sculptures. Texture analyses of the computed tomography images were carried out using the gray-level co-occurrence matrix, from which 15 textural features were calculated. The k-nearest-neighbor algorithm combined with cross validation was applied for classification and evaluation of the system. Input datasets with a variation in image qualities (resolution, gray level, and image size) were investigated using this novel system, and the accuracy was greater than 98 % when the input images had a certain quality level. Although there are still technical problems to be overcome, progress in the development of automated identification is extremely encouraging in that such an approach has the potential to make a valuable contribution in adding scientific species notion to the artifacts; otherwise, only the literal documents are available.