Abstract
The wood industry is facing many challenges. The high variability of raw material and the complexity of manufacturing processes results in a wide range of visible structure defects, whichhave tobe controlled by trained specialists.These manual processes are not only tedious and biased, but also less effective. To overcome the drawbacks of the manual quality control processes, several automated vision-based systems have been proposed. Even though some conducted studies achieved a higher recognition rate than trained experts, researchershave todeal with a lack of large-scale databases and authentic data in this field. To address this issue, we performed a data acquisition experiment set in the industrial environment, where we were able to acquire an extensive set of authentic data from a production line.For this purpose, we designed and implemented a complex technical solution suitable for high-speed acquisition during harsh manufacturing conditions. In this data note, we present a large-scale dataset of high-resolution sawn timber surface imagescontaining more than 43 000 labelledsurface defectsand covering 10 types of the most common wood defects. Moreover, with each image record, we provide two types of labels allowing researchers to perform semantic segmentation, as well as defect classification, and localization.
Highlights
In the wood industry, each step of the manufacturing process affects material utilization and cost efficiency.[1]
The heterogeneity of wood material with the complexity of these manufacturing processes may result in various defects, which degrade the mechanical properties of the wood such as the strength and stiffness and reduce its aesthetic value.[2]
We had to deal with the high speed of the sawmill conveyor belt, which reached a value of 9.6 m sÀ1 at the place of the acquisition
Summary
Each step of the manufacturing process affects material utilization and cost efficiency.[1]. According to the repeatability and quality of the inspection, the study performed by Lycken[7] has already proved that automatic systems slightly outperformed human graders Most of these systems were based on conventional image processing techniques in combination with supervised learning algorithms, over the last decade deep learning has achieved remarkable success in the forestry and wood products industry.[8] researchers in the field were able to achieve satisfying results with the average recognition rate above 90 %,9 most of the authors worked with small-scale image datasets obtained in laboratory conditions by using self-developed vision system setups. To provide more valuable information in this data descriptor, all dataset samples were complemented with two types of labels: a semantic label map for the semantic segmentation and a bounding box label
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.
