Automatic estimation of annual ring profiles in Norway spruce timber boards using optical scanning and deep learning
Osama Abdeljaber, Tadios Habite, Anders Olsson
Abstract
In softwood species, annual ring width correlates with various timber characteristics, including the density and modulus of elasticity along with bending and tensile strengths. Knowledge of annual ring profiles may contribute to more accurate machine strength grading of sawn timber. This paper proposes a fast and accurate method for automatic estimation of ring profiles along timber boards on the basis of optical scanning. The method utilizes two 1D convolutional neural networks to determine the pith location and detect the surface annual rings at multiple cross-sections along the scanned board. The automatically extracted rings and pith information can then be used to estimate the annual ring profile at each cross-section. The proposed method was validated on a large number of board cross-sections for which the pith locations and radial ring width profiles had been determined manually. The paper also investigates the potential of using the automatically estimated average ring width as an indicating property in machine strength grading of sawn timber. The results indicated that combining the automatically estimated ring width with other prediction variables can improve the accuracy of bending and tensile strength predictions, especially when the grading is based only on information extracted from optical and laser scanning data.