Wood is widely used in construction, the home, and art applications all over the world because of its good mechanical properties and aesthetic value. However, because the growth and preservation of wood are greatly affected by the environment, it often contains different types of defects that affect its performance and ornamental value. To solve the issues of high labor costs and low efficiency in the detection of wood defects, we used machine vision and deep learning methods in this work. A color charge-coupled device camera was used to collect the surface images of two types of wood from Akagi and Pinus sylvestris trees. A total of 500 images with a size of 200 × 200 pixels containing wood knots, dead knots, and checking defects were obtained. The transfer learning method was used to apply the single-shot multibox detector (SSD), a target detection algorithm and the DenseNet network was introduced to improve the algorithm. The mean average precision for detecting the three types of defects, live knots, dead knots and checking was 96.1%.
The deep learning feature extraction method and extreme learning machine (ELM) classification method are combined to establish a depth extreme learning machine model for wood image defect detection. The convolution neural network (CNN) algorithm alone tends to provide inaccurate defect locations, incomplete defect contour and boundary information, and inaccurate recognition of defect types. The nonsubsampled shearlet transform (NSST) is used here to preprocess the wood images, which reduces the complexity and computation of the image processing. CNN is then applied to manage the deep algorithm design of the wood images. The simple linear iterative clustering algorithm is used to improve the initial model; the obtained image features are used as ELM classification inputs. ELM has faster training speed and stronger generalization ability than other similar neural networks, but the random selection of input weights and thresholds degrades the classification accuracy. A genetic algorithm is used here to optimize the initial parameters of the ELM to stabilize the network classification performance. The depth extreme learning machine can extract high-level abstract information from the data, does not require iterative adjustment of the network weights, has high calculation efficiency, and allows CNN to effectively extract the wood defect contour. The distributed input data feature is automatically expressed in layer form by deep learning pre-training. The wood defect recognition accuracy reached 96.72% in a test time of only 187 ms.
Solid wood panels are widely used in the wood flooring and furniture industries, and paneling is an excellent material for indoor decoration. The classification of colors helps to improve the appearance of wood products assembled from multiple panels due to the differences in surface colors of solid wood panels. Traditional wood surface color classification mainly depends on workers’ visual observations, and manual color classification is prone to visual fatigue and quality instability. In order to reduce labor costs of sorting and to improve production efficiency, in this study, we introduced machine vision technology and an unsupervised learning technique. First-order color moments, second-order color moments, and color histogram peaks were selected to extract feature vectors and to realize data dimension reduction. The feature vector set was divided into different clusters by the K-means algorithm to achieve color classification and, thus, the solid wood panels with similar surface color were classified into one category. Furthermore, during twice clustering based on second-order color moment, texture recognition was realized on the basis of color classification. A sample of beech wood was selected as the research object, not only was color classification completed, but texture recognition was also realized. The experimental results verified the effectiveness of the technical proposal.
Solid wood flooring has good esthetic properties and is an excellent material for interior decoration. To meet the artistic effects of specific interior decoration requirements, the color of solid wood flooring needs to be coordinated. Thus, the color of the produced solid wood flooring needs to be sorted to meet the individual needs of customers. In this work, machine vision, deep learning methods, and ensemble learning methods are introduced to reduce the cost of manual sorting and improve production efficiency. The color CCD camera was used to collect 108 solid wood floors of three color grades provided by the company and obtained 108 18,000 × 2048 pixel wood images. A total of 432 images were obtained after data expansion. Deep learning methods, such as VGG16, DenseNet121, and XGBoost, were compared. After using XGBoost to filter the features, the accuracy of solid wood flooring color classification was 97.22%, the training model time was 5.27 s, the average test time for each picture was 51 ms, and a good result was achieved.
In the production process for wooden furniture, the raw material costs account for more than 50% of furniture costs, and the utilization rate of raw materials depends mainly on the layout scheme. Therefore, a reasonable layout is an important measure to reduce furniture costs. This paper investigates the solid wood board cutting stock problem (CSP) and establishes an optimization model, with the goal of the highest possible utilization rate for original boards. An ant colony-immune genetic algorithm (AC-IGA) is designed to solve this model. The solutions of the ant colony algorithm are used as the initial population of the immune genetic algorithm, and the optimal solution is obtained using the immune genetic algorithm after multiple iterations are transformed into the accumulation of global pheromones, which improves the search ability and ensures the solution quality. The layout process of the solid wood board is abstracted into the construction process of the solution. At the same time, in order to prevent premature convergence, several improved methods, such as a global pheromone hybrid update and adaptive crossover probability, are proposed. Comparative experiments are designed to verify the feasibility and effectiveness of the AC-IGA, and the experimental results show that the AC-IGA has better solution precision and global search ability compared with the ant colony algorithm (ACA), genetic algorithm (GA), grey wolf optimizer (GWO), and polar bear optimization (PBO). The utilization rate increased by more than 2.308%, which provides effective theoretical and methodological support for furniture enterprises to improve economic benefits.
Sawn timber is an important component material in furniture manufacturing, decoration, construction and other industries. The mechanical properties, surface colors, textures, use and other properties of sawn timber possesed by different tree species are different. In order to meet the needs of reasonable timber use and product quality of sawn timber products, sawn timber must be identified according to tree species to ensure the best use of materials. In this study, an optimized convolution neural network was proposed to process sawn timber image data to identify the tree species of the sawn timber. The spatial pyramid pooling and attention mechanism were used to improve the convolution layer of ResNet101 to extract the feature vector of sawn timber images. The optimized ResNet (simply called “AM-SPPResNet”) was used to identify the sawn timber image, and the basic recognition model was obtained. Then, the weight parameters of the feature extraction layer of the basic model were frozen, the full connection layer was removed, and using support vector machine (SVM) and XGBoost classifier which were commonly used in machine learning to train and learn the 21 × 1024 dimension feature vectors extracted by feature extraction layer. Through a number of comparative experiments, it is found that the prediction model using linear function as the kernel function of support vector machine learning the feature vectors extracted from the improved convolution layer performed best, and the F1 score and overall accuracy of all kinds of samples were above 99%. Compared with the traditional methods, the accuracy was improved by up to 12%.