collage

Project: Detection of defects on wood surfaces on the basis of optical scanning

The purpose of this research project is to gain increased knowledge and a better understanding of how different wood characteristics and surface defects of timber boards can be identified and detected in a more robust manner than possible today, and how such identification can be used to add value to the timber engineering (wood manufacturing) industry.

Project information

Project manager
Anders Olsson
Other project members
Jan Oscarsson, Tadios Sisay Habite, Osama Abdeljaber
Participating organizations
Linnaeus University, ProWood
Financier
The Knowledge Foundation
Timetable
2017–2022
Subject
Building technology (Department of Building Technology, Faculty of technology)

More about the project

Different mechanical and physical properties of wood from softwood species can be related to the distance to the pith of the log. Hence, knowledge of location of pith and annual ring width in relation to board cross-sections, and how these properties vary in the longitudinal direction of boards, is relevant for many purposes, such as assessment of mechanical properties and shape stability of sawn timber. Knowledge of the pith location is also needed to establish detailed and accurate three-dimensional (3D) models of sawn timber, including geometry of knots and local fiber orientation on the basis of surface scanning.

Therefore, a purpose of the project is to examine the possibility of developing accurate and robust methods and algorithms to detect surface annual rings and estimate the pith location along the length direction of timber boards. The data used as basis for the work is obtained from optical and laser scanning of longitudinal surfaces of timber boards. Different signal processing methods, like wavelet transform, and machine learning algorithms, such as multi-layer perceptrons and generative adversarial networks, are employed in the process.

The results of the project will be applied to improve strength grading of structural timber and lamellas for engineered wood products. Furthermore, knowledge about pith location and annual ring pattern can be utilized also for other purposes within timber industries, e.g. to optimize the manufacturing yield of products and make use of the full aesthetical and structural potential of timber/wood material.

This doctoral research is being conducted within the industrial research school ProWood+ and in collaboration with industry. The project is part of the research in the Strength Grading of Timber research group.

Staff