Wood Species Recognition Based on Visible and Near-Infrared Spectral Analysis Using Fuzzy Reasoning and Decision-Level Fusion

A novel wood species spectral classiﬁcation scheme is proposed based on a fuzzy rule classiﬁer. The visible/near-infrared (VIS/ NIR) spectral reﬂectance curve of a wood sample’s cross section was captured using a USB 2000-VIS-NIR spectrometer and a FLAME-NIR spectrometer. First, the wood spectral curve—with spectral bands of 376.64–779.84 nm and 950–1650nm—was processed using the principal component analysis (PCA) dimension reduction algorithm. The wood spectral data were divided into two datasets, namely, training and testing sets. The training set was used to generate the membership functions and the initial fuzzy rule set, with the fuzzy rule being adjusted to supplement and reﬁne the classiﬁcation rules to form a perfect fuzzy rule set. Second, a fuzzy classiﬁer was applied to the VIS and NIR bands. An improved decision-level fusion scheme based on the Dempster–Shafer (D-S) evidential theory was proposed to further improve the accuracy of wood species recognition. The test results using the testing set indicated that the overall recognition accuracy (ORA) of our scheme reached 94.76% for 50 wood species, which is superior to that of conventional classiﬁcation algorithms and recent state-of-the-art wood species classiﬁcation schemes. This method can rapidly achieve good recognition results, especially using small datasets, owing to its low computational time and space complexity.


Introduction
Wood species classification has been investigated for several years, as different wood species have diverse physical and chemical properties. Many such schemes have been proposed for automatic processing using sensors and computers, with spectra-based [1][2][3], chemometric-based [4], and image-based schemes [5][6][7][8][9] being the most commonly investigated. Spectral analysis technology is also widely used in the prediction of wood properties [10][11][12] such as wood density [13], wood moisture content [14,15], and others [16,17]. e NIR spectral band is often used in these applications. A wood spectral analysis scheme usually pertains to one-dimensional (1D) spectral reflectance curves, which exhibits low computational complexity and, thus, high processing speeds. A wood image processing scheme usually considers the wood's texture features for species classification, as its texture is more stable than its color [18][19][20].
Fuzzy logic can provide nonseparated output classes and functions well with just a few learning datasets. In the past, fuzzy-rule-based schemes were successfully used in control systems and pattern recognition applications [21,22]. In the wood industry, fuzzy rule classification has been successfully applied to wood color classification and wood defect recognition [23][24][25]. For example, considering the uncertainty of wood color and processing speed, Bombardier et al. proposed a fuzzy rule classifier to fulfill wood color recognition [24,25].
Fuzzy rule classification is not frequently used in wood species recognition. However, Ibrahim et al. proposed a fuzzy preclassifier to classify 48 tropical wood species into four broad categories, followed by the use of a support vector machine (SVM) classifier in each broad category to further determine the wood species of a sample [19]. One advantage of their approach was that when a new wood species was added to the system, only the SVM classifier of one broad category required retraining instead of the entire system. Similarly, Yusof et al. also proposed a fuzzy-logic-based preclassifier to classify tropical wood species into four broad categories, followed by performing specific wood species recognition using definite classifiers to increase recognition accuracy and decrease processing time requirements [7].
In this study, we propose a fuzzy rule classification scheme for the recognition of 50 wood species using 1D spectral reflectance data. e spectral range covers both the visible (VIS) band (i.e., 376.64-779.84 nm) and the nearinfrared (NIR) band (i.e., 950-1650 nm). For the wood spectral curves, the VIS band may vary as the color of a wood sample may change owing to environmental variations, while the NIR band remains relatively stable. Consequently, these two bands were processed using different fuzzy classifiers, and the two classification results were further processed using an improved decision-level fusion based on the D-S evidential theory.
Our scheme has the two following advantages. First, it can achieve good recognition accuracy rapidly in a small spectral dataset. ere are only 50 samples for each wood species, and each sample consists of a VIS spectral curve and an NIR curve. Second, the experimental equipment cost is low. e used Ocean Optics USB2000-VIS-NIR spectrometer costs approximately $3,000, while the Ocean Optics FLAME-NIR spectrometer costs $8,000. Several comparisons with other classical and state-of-the-art classifiers in wood species recognition also verified the merits of our scheme.

Wood Samples and Spectral Data Acquisition.
Our wood dataset consists of 50 wood species, as shown in Table 1 and Figure 1. ese 50 wood species consist of softwood and hardwood species, which are representative tree species in the wood market. Moreover, this dataset also consists of some similar wood species (i.e., visually similar wood species and intragenus different species). Each wood sample was processed into a 2 × 2 × 3 cm block. We used the Ocean Optics USB2000-VIS-NIR microfiber spectrometer and an Ocean Optics FLAME-NIR microfiber spectrometer, visible and near-infrared (VIS/NIR) spectra of the wood samples being obtained using these devices. Fifty mean spectral curves were detected by using the spectrometer for each wood species-that is, there are 2500 VIS spectral curves and 2500 NIR spectral curves for 50 wood species. Our experimental setup consisted of a halogen lamp, a universal serial bus, a computer, a customized holder, a fiber spectrometer, and a section of optical fiber, as shown in Figure 2. Spectral acquisition was performed in a controlled environment at a temperature interval of 20 ± 2°C. e VIS spectral band covered a range of 376.64-779.84 nm, with a spectral resolution of approximately 0.3 nm. e NIR spectral band covered a range of 950-1650 nm, with a spectral resolution of approximately 5.4 nm. e spectrometer parameter settings, spectral data acquisition, and data storage were conducted using the Spectrasuite software. e integration time was 300 ms, and the mean number of measurements at each point was 900. Before spectral acquisition, the reference and dark spectra were measured and stored, the reference spectra were acquired using a standard white panel of known 100% reflectance, and the dark spectra were acquired by blocking the radians. For each wood sample, four diffuse reflectance spectra were measured randomly using (1)where I R , I B , and I W represented the received intensity, dark intensity, and white panel intensity, respectively-at different locations across the wood sample's cross section. In fact, wood cross section has plentiful wood structures such as pores and parenchyma, making its spectra more suitable for species recognition, which is superior to radial direction and tangential direction in wood species recognition [26] and wood density prediction [13]. Subsequently, the mean spectrum of each wood sample was calculated and stored for subsequent spectral analysis and species classification.
e spectral range of the USB2000-VIS-NIR spectrometer was 340-1027 nm. Both ends of this spectral range can be noisy, so the useful spectral range is 376.64-779.84 nm. e spectral data in the VIS band may be variable as the color of a wood sample may change with changing environmental conditions. To avoid this, we maintained a stable environment during spectral acquisition and wood sample preservation. e NIR band of 950-1650 nm is relatively stable and can be used to characterize different wood properties to some extent. erefore, these two bands were processed using different fuzzy classifiers-that is, with different membership functions and fuzzy rules-the two classification results of which were further processed using an improved decision-level fusion based on the D-S evidential theory.

Spectral Dimension Reduction.
For each spectral curve, the VIS/NIR band includes thousands of spectral data, so that the spectral dimension is very large. Consequently, each spectral curve contains redundant information, which reduces the wood species classification accuracy and speed. We used principal component analysis (PCA) and the T-distributed stochastic neighbor embedding (T-SNE) algorithms to compare and reduce the spectral dimension results. e PCA algorithm is a transformation algorithm in multivariate statistics, which is based on the variance maximization of a mapped low-dimension vector. e procedure is as follows: First, the initial dataset matrix is defined as A m×n � [a 1 , . . . , a n ]-where m and n are the dimension and number of feature vectors, respectively. e mean vector is computed as u � (1/n) n i�1 a i . Second, we compute x i � a i − u to form X m×n � [x 1 , . . . , x n ]. ird, the k largest eigenvalues of XX T are selected, their k corresponding eigenvectors ε 1 , . . . , ε k forming a matrix D � [ε 1 , . . . , ε k ]. Finally, the new dataset matrix after dimension reduction is computed as D T × X � P k×n (k < m).    Table 1 (see Table 1 for specific wood species names).  Additionally, the T-SNE algorithm was also used for spectral dimension reduction.
is algorithm performs nonlinear dimension reduction, an improvement on the original SNE algorithm [27]. e algorithm is based on the invariant data distribution probability of the mapped lowdimensional vector. Here, the symbol "T" in T-SNE represents the t-distribution, the freedom of the t-distribution being 1 in this study. e graphs of the three-dimensional (3D) spectral vectors for the VIS and NIR bands after spectral dimension reduction using the PCA and T-SNE algorithms are shown in Figure 5. e contribution rate (CR) and cumulative contribution rate (CCR) of the first ten principal components are shown in Figure 6 and Table 2 for the VIS and NIR bands. In Figure 5, the wood sample's 3D spectral vectors were acquired using the PCA and T-SNE algorithms and are shown with 50 different colors for the 50 wood species. e best case is shown in Figure 5(b), where the wood samples were the most dispersed.

Fuzzy Rule Classifier.
A fuzzy rule classifier is a fuzzy reasoning system based on fuzzy linguistic rules, its core component being a fuzzy rule set. When an input sample is transformed into the rule set of one wood species, this sample is then classified as a wood species. e overall fuzzy reasoning system is shown in Figure 7 and consists of two parts: the training and testing processes. e steps in Figure 7 are presented as follows.
Step 1. e membership functions are set to fuzzify the training sample's feature and generate the training sample's fuzzy rules Step 2. Fuzzy rules are adjusted by using a corrected confidence coefficient Step 3. e fuzzy rule set is generated Step 4. e testing sample's feature is fuzzified, and the generated rule is compared with the fuzzy rule set for wood species classification e training process consisted of three steps. First, membership functions were used to fulfill the fuzzification of the training dataset. Here, the membership functions could be a triangular function, trapezoid function, or Gaussian function. Second, fuzzy rules were generated based on the wood species of the wood samples in the training dataset. A fuzzy rule was defined as "IF . . . AND . . ., THEN . . ." using the conjunction or disjunction operation. ird, the fuzzy rules required modification using a confidence coefficient to form a perfect fuzzy rule set.
In the testing process, the testing dataset was added to the trained fuzzy rule classifier, and the same membership functions were used to fulfill its fuzzification. In this way, a corresponding fuzzy rule of a testing sample could be obtained, and this rule was compared with the generated perfect fuzzy rule set to obtain the classified wood species.
is species was then compared with the correctly labeled species of the testing sample to evaluate the performance of the fuzzy rule classifier. If the corresponding fuzzy rule of a testing sample was not found in the perfect fuzzy rule set, the sample was classified as an unknown species.

Fuzzification of the Feature Vector.
Here, the feature vector refers to the spectral vector after dimension reduction.
is fuzzification step transforms spectral feature vectors into linguistic variables. A linguistic variable is defined using a triple value (V, X, T V ), where V is a variable (e.g., PC1) defined on a set of reference X, X is the universe of discourse (field of variation of V ), and T V is the vocabulary chosen to describe the values of V in a symbolic way.
e set T V � A 1 , A 2 , . . . contains the normalized fuzzy subsets of X, and each fuzzy subset A i is defined by the membership degree u A i .
For example, the wood spectral feature vector is obtained using the PCA algorithm. e fourth principal component (PC4) of the first ten wood species is shown in Table 3 for the NIR band, where the maximum, minimum, mean, and median values of PC4 are shown. us, we can design the membership functions to divide the NIR PC4 (i.e., the 4 th dimension) into twenty-six intervals T V � A 1 , A 2 , . . . , A 26 based on these values, as shown in Figure 8.
As the different spectral PCs or dimensions may be divided into different intervals, the overall number of fuzzy rules is the product of the interval number of different PCs or dimensions: where N is the dimension of the spectral feature vectors and Card(T V ) is the number of intervals for variable V (i.e., the element of the spectral feature vector). In fact, N rules can be determined by both N and Card(T V ). erefore, a large N or Card(T V ) produces a large N rules resulting in high computational complexity. In other words, N and Card(T V ) should be designed to be as small as possible in view of the recognition accuracy of our fuzzy rule classifier. If they cannot be simultaneously small, the dimension N should be as small as possible.
For instance, if the PCA algorithm is used for wood spectral dimension reduction, the CCR should be above 99% in view of the PC number. As can be seen from Table 2, the CCR of the first four PCs reaches 99% and 99.35% for the VIS and NIR bands, respectively, but remains approximately stable when N > 4, so we should set N ≥ 4.
After several tests with the PCA algorithm, N and Card(T V ) were as follows: for the VIS band, e triangular, trapezoid, and triangular-trapezoid functions were used and compared 50 times-in terms of the ORA and mean training time requirement (i.e., the wood sample number of the training set was 2000) for the fuzzy rule set-as described in Tables 4 and 5 for the VIS and NIR bands, respectively. e maximum and practical N rules in    terms of N and Card(T V ) are listed in Table 6. We observed that the training time requirement for the fuzzy rule set was practically invariant with regard to the fuzzy classifiers based on different membership functions. However, this time requirement was only relevant to the N dimension of the spectral feature vectors. In fact, both the time requirement        Journal of Spectroscopy 7 three linguistic variables are considered for input (V 1 , V 2 , V 3 ) and the output is wood species Y, the fuzzy rule is as follows: is expression indicates that when V 1 is classified as A I , V 2 is classified as B J . . ., and the output class is Class l . erefore, we need to calculate the membership degrees In this expression, "AND" is a Cartesian product between the linguistic variables and the operation is performed with a T-Norm, as follows: is equation is then used to calculate the product of the membership degrees for the spectral linguistic variables For one wood sample of wood class/species l, there are often some products of the membership degrees β s Class l ≠ 0, s � 1, 2, . . . , S. For example, if u A 1 , u A 3 , u A 4 , u B 1 , u B 5 , u C 1 are not equal to 0, we obtain 3 × 2 × 1 � 6 products of the membership degrees for one wood sample (i.e., β s Class l , s � 1, 2, . . . , 6). We should then choose the largest product to form the corresponding rule. us, we obtain a fuzzy rule for wood class/species l as follows:

Fuzzy Rule Adjustment.
When the fuzzy rule is generated, there are usually several rules with the same judgment condition (i.e., the same "IF . . . AND . . .,") but different classification results (i.e., different "THEN . . .").
Consequently, fuzzy rule adjustment is usually required to add a confidence coefficient (CC) to each fuzzy rule. First, for one wood sample of wood class/species l, the sum of the products of the membership degrees β s Class l ≠ 0, s � 1, 2, . . . , S is calculated as follows: en, the mean value is calculated using us, we can compute the CC of the fuzzy rule produced as follows: Moreover, when the same rules are produced by other samples, the CC of the fuzzy rule should be increased as follows: If the same rule is not produced by other samples, the CC of this fuzzy rule remains invariant. Some final rules with their CCs are listed in Table 7. In practical classification work, when there are rules that have the same judgment condition but different classification results, the final classification is determined by the fuzzy rule with the largest CC.

Decision-Level Fusion.
e D-S evidential theory [28] is an effective decision-level fusion scheme, but the classifier's reliability is not considered fully when each classifier's result is converted into a classification probability distribution before the decision-level fusion. To solve this problem, we proposed an improved D-S decision-level fusion method that determines each classifier's weight in view of the differences in the classification accuracy ratio and correlation coefficient.
As the NIR band is more stable than the VIS band, these two bands should be processed using different fuzzy parameters (e.g., different membership functions). Consequently, spectral dimension reduction and fuzzy rule classification were applied to the two bands, respectively, so that the two classification results could be fused with our improved D-S decision-level fusion, as described below. e overall improved D-S decision-level fusion model is shown in Figure 9. e steps in Figure 9 are outlined as follows: Step 1. e basic classification probability distribution of two classifiers is generated using classification results Step 2. Classifier weights are determined using classification the accuracy ratio (CAR) and classification correlation coefficient (CCC) Step 3.
e adjusted classification probability distribution is generated using classifier weights where n is the maximum rule number such that n � 951825 for r VIS � 4 and n � 1368640 for r NIR � 4. Rule dim1 l , . . . , Rule dimr l refers to rule l with product β l . en, the rows with β l � 0 are deleted in this matrix. e rule Rule dim1 l , . . . , Rule dimr l in every row in the matrix Tar is checked to determine whether it belongs to the fuzzy rule set- e added final column Out nl refers to the corresponding wood species. Some rules in Tar pro correspond to the same wood species (i.e., Out ni � Out nj for i ≠ j). For an Out nl that corresponds to several rules, the maximum rule (i.e., with the largest β ni ) remains, while the others are deleted, so that the matrix Tar out is formed. erefore, for one wood sample, the classification probability distribution can be computed as follows: Here, nlast is the number of Tar out . Note that, for wood species that do not exist in Tar out , their corresponding classification probabilities are set as 0. For example, the classification probability distribution in the VIS and NIR bands for a wood sample is shown in Table 8.

Weight Determination of VIS and NIR Fuzzy Rule
Classifier. In this section, we propose a novel classifier's weight determination based on the difference between the fuzzy classification accuracy ratio (CAR) and the correlation coefficient for the VIS and NIR bands using an analytical hierarchy process. In Section 2.3.1, we concluded that the fuzzy classification accuracy was 90.20% after the PCA algorithm processing for r VIS � 4, while it was 93.25% for r NIR � 4 in the training set.
Regarding the calculation of the classification correlation coefficient (CCC), the training set is used to calculate the classification probability distribution for each wood sample using (13). en, the following equation is used to calculate the CCC for the VIS and NIR classifiers: Here, Cov(x, y) refers to the covariance between the corrected and actual classification probability distributions. For instance, as described in Table 8, the actual classification probability distribution for one wood sample for the NIR and VIS classifiers was [0, 0, 0, 0, 0, 2.75, 0, . . . , 0, 0] and [0, 0, 0, 0, 0, 27.22, 0.74, . . . , 0.51, 0], respectively, while the corrected one was [0, 0, 0, 0, 0, 1, 0, . . . , 0]. e σ x , σ y represent the standard deviations for the corrected and actual classification probability distribution vectors in the training set, respectively. e computed fuzzy CCC was 0.8073 after PCA algorithm processing for r VIS � 4, whereas it was 0.8862 for r NIR � 4. e difference in the CAR was Diff CAR � |CAR VIS − CAR NIR | � 0.0350, while that of CCC was Diff CCC � |CCC VIS − CCC NIR | � 0.0789. e membership functions are shown in Figure 10. e corresponding credibility for these interval differences is shown in Table 9. We observed that the Diff CAR was in the 1 st interval, which indicated that the VIS fuzzy and NIR fuzzy classifiers had the same credibility in view of the CAR, while Diff CCC was in the 2 nd interval, which indicated that the NIR fuzzy classifier was more credible than the VIS classifier in view of the CCC. To determine the classifier's weight using (17), we first need to compute the classifier's scores using (15) and then compute the mean score using (16): Weight VIS � Score VIS Score mean � 2 3 ,

Improved D-S Decision-Level Fusion Based on the
Classifier's Weight. In this section, we modified the classification probability distribution, as shown in Table 8, in the VIS and NIR bands using the weight of the classifier. First, the maximum probability was modified using (18), and then, we computed the sum of this modified maximum probability with the other 19 probabilities using (19). Finally, we obtained the modified classification probability distribution using (20). As an example, the classification probability distribution in Table 8 was modified in this manner, as shown in Table 10.
Finally, we used the modified VIS and NIR classification probability distributions to compute the normalized constant and composed mass function as follows (i.e., m(A i ) � P mod i ): Here, A i is the i th wood species with i � 1, 2, . . . , 50. Based on these equations, we can compute 50 mass functions mass(A i ), i � 1, 2, . . . , 50. e first two largest mass(A i ) are defined as mass max 1 (A i ), mass max 2 (A i ), respectively. mass(f) refers to the mass function for an uncertain set, and in our wood species, the recognition work mass(f) � 0. Wood sample x is then classified as wood species A j with the following rules: mass(A j ) � mass max 1 (A i ), ε 1 � 0.15, ε 2 � 0.01). Otherwise, the judgment is the "rejected classification":

Results and Comparisons
In our experiments, there were 2,500 spectral curves for 50 wood species. ese samples were divided into a training set and a testing set using k-fold cross validation [29] with k � 5, so that the training set consisted of 2000 samples and the testing set consisted of 500 samples. Consequently, there were 40 training samples and 10 testing samples for each wood species. e PC1 and PC2 of the training and testing datasets were distributed as shown in Figure 11, where the distributions of both the training and testing sets were dispersed and uniform, indicating that the dataset was suitable for pattern classification.

Comparisons with Conventional
Algorithms. e fuzzy rule classifier was applied to the wood species spectral classification experiments and compared with other important classification schemes, such as the Bayes classifier (BC) [30], random forest (RF) [31], BP network (BPN) [32], SVM [33], and LeNet-5 [34]. e overall recognition accuracy (ORA) and processing speed for a testing sample from our testing dataset (i.e., time requirement, TR) are listed in Table 11. e computer configurations used are presented in Table 12. e ORA was calculated as follows (i.e., n right is the sample number correctly classified, and n test is the total sample number of testing sets): In the RF classification, the time complexity was O(m · n test · d)-where m is the feature dimension, d is the tree depth, and the RF number is 500. In the BP classification, the time complexity was O(n test · d−1 i�1 n i n i+1 )--where n i refers to the node number of the i th layer and d refers to the overall layer number, including the input and output layers. e structure of the BP network was 7 (input -where M i is the size of the output feature image in the i th layer, K i is the size of the convolution cores in the i th convolutional layer, C i is the core number of the i th convolutional layer, and d is the overall convolutional layer number. In the SVM classification, a linear kernel function for the PCA algorithm and a radial basis function (RBF) for the T-SNE were used with a penalty factor of 1.2.
In our fuzzy reasoning classifier (FRC) classification, we observed that the PCA algorithm performed much better than the T-SNE algorithm in terms of spectral dimension reduction. e best ORA of 96.3636% was achieved with our FRC, and the D-S decision-level fusion scheme was improved with the use of four PCs for the VIS band and six PCs for the NIR band, with a TR of 2.535915 ms for one testing sample.
In other words, the RF algorithm could achieve good and efficient classification results using a large training dataset. However, its classification performance was poor with our small dataset-our training dataset only consisted of 2000 wood samples-and with low-dimensional feature vectors. Similarly, the BP neural network and LeNet-5 also required a large training dataset to complete network training. Regarding spectral dimension reduction, the classification results using our FRC and T-SNE were relatively poor compared with those of the PCA algorithm as the T-SNE is a nonlinear dimension reduction algorithm.

Comparisons with State-of-the-Art Algorithms.
We compared the proposed scheme with other state-of-the-art wood species recognition schemes, all of which performed wood species classification using digital images of wood sample cross sections. We set up the image collection experimental equipment, as shown in Figure 12, consisting of a charge-coupled device (CCD) camera, an optical microscope with a magnification ratio of 10-100, and a light-emitting diode (LED) light source. e wood color image selected was of size 1600 × 1200 pixels and magnification ratio 50. We used this imaging equipment to capture the cross-sectional color image of each wood sample so that each species included 50 images. is color image was then converted into a grayscale image of size 400 × 300 pixels, although the color image was used in the CNN scheme. e computer configuration used is presented in Table 13, and the classification performance comparison is given in Table 14. We found that our FRC and improved D-S decision-level fusion scheme outperformed all other state-of-the-art classification schemes in terms of ORA.
In these state-of-the-art wood species recognition schemes, Yusof et al. employed texture feature operators (e.g., basic gray-level aura matrix (BGLAM), improved basic gray-level aura matrix (I-BGLAM)), and pore distribution features (i.e., statistical properties of pores distribution        [39] SqueezeNet 86.28 [40] ResNet18 94.40 [41] GoogLeNet 92.80 [42] CNN 83.00 (SPPD)) and several feature extraction algorithms, such as the genetic algorithm (GA) and kernel discriminant analysis (KDA) to classify more than 50 tropical wood species [18,19,35,37]. However, their schemes were only suitable for the classification of hardwood species with pores. For softwood species without pores, the classification performance of their schemes was poor. Because our 50 wood species consist of both hardwood and softwood species, their schemes delivered poor classification results. Another texture feature operator, the local binary pattern (LBP), and a deep learning neural network were also used for classification comparisons [36,[38][39][40][41][42].

Conclusions
In this study, a novel wood species spectral classification scheme was proposed based on a fuzzy linguistic rule classifier and an improved decision-level fusion technique based on the D-S evidential theory. e VIS/NIR spectral reflectance curves of a wood sample's cross section were measured using a USB 2000-VIS-NIR spectrometer and a FLAME-NIR spectrometer.
As the VIS and NIR bands for the wood sample's cross section have different spectral stabilities, they were processed using two different FRCs, and their classification results were further fused using an improved decision-level fusion technique based on the D-S evidential theory. e test results showed that the best ORA of our scheme reached 94.76% for 50 wood species, with little computational overhead. More generally, our scheme has the following advantages compared with existing wood species recognition schemes. First, the acquired wood spectral curves were usually noisy and variable because of the variability of the external environment-such as optical illumination intensity-and the wood sample's internal factors-such as humidity, surface roughness, and intraspecies differences. e uncertainty of these wood spectral features could be resolved using fuzzy processing to some extent. Second, our scheme rapidly achieved good recognition results, particularly with small datasets, and the cost of the VIS/NIR spectrometer used was relatively low. e spectral dataset was a 1D signal set, which had a relatively low computational overhead compared to other 2D image datasets. erefore, our scheme could be readily applied to wood recognition and classification in the industry in the near future.
However, our scheme can only classify the known wood species which is included in our training dataset. In practical work, some unknown wood species samples may be encountered by our wood classification system. is issue is an unknown species identification problem under the open-world assumption, which can be solved in the certainty or uncertainty framework. For example, in an uncertainty framework, Tang et al. have proposed a new method for generation of generalized basic probability assignment (GBPA) based on evidence theory [43]. In this method, the maximum, minimum, and mean values were used to produce triangular fuzzy number of each class in different attributes, and the intersection points of test samples with triangular fuzzy numbers were calculated. Based on this method, it is feasible to produce a classifier which can effectively recognize the known and unknown classes. erefore, we plan to investigate and improve this method for wood species classification, since the wood species quantity is greatly larger than the class quantity in [43]. On the other hand, in a certainty framework, we have also used a one-class classifier Support Vector Data Description (SVDD) [44], which can preclassify the wood samples into two categories (i.e., the known and unknown wood categories).

Data Availability
Access to research data is restricted. e experimental instruments and wood species samples are owned by other academic institutions; therefore, we cannot publicly release the research spectral and image wood dataset.

Conflicts of Interest
e authors declare no conflicts of interest.