Abstract
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%.
Highlights
Wood plays an important role as an essential raw material in many industries, especially in the home and construction industries
Compared with the worst-performing mathematical morphology and ResNet152, the precision of the model proposed in this paper was improved by 12.7% to 96.1%, which met the precision requirement of not less than 95% of wood processing enterprises
We adopted the transfer learning method to apply the traditional single-shot multibox detector (SSD) algorithm to solid wood board defect recognition, and the stochastic gradient descent (SGD) method and the Adam optimizer applied to the solid wood board defect data were compared in the training performance of the traditional SSD algorithm to obtain a better loss function optimizer
Summary
Wood plays an important role as an essential raw material in many industries, especially in the home and construction industries. Chinese consumers prefer to buy solid wood materials without knots, checkings and wormholes. In order to meet consumer t demand for solid wood panels, Chinese wood processing enterprises are required to spend a lot on labor costs to identify the defects on the surface of solid wood panels, so as to eliminate the defects by sawing and splice the remaining materials into certain specified plate products through finger joint technology (Figure 1), while reducing wood waste and increasing the economic benefits. The use of manpower to identify the surface defects of solid wood panels has many disadvantages such as strong subjectivity, low work efficiency, high labor intensity, and high cost. More and more wood processing enterprises have introduced automation and intelligent wood detection technology to replace humans to identify and detect the quality of the wood, improve work efficiency, reduce costs and increase profits [1]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
