Knowledge of annual ring width and location of pith 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 shape mechanical properties and stability of sawn timber. Hence, the present research aims at developing a novel method and an algorithm, based on data obtained from optical surface scanning, by which the pith location along the length of sawn timber boards can be determined accurately and automatically. The first step of the method is to identify clear wood sections, free of defects along boards. Then time-frequency analysis, using the continuous wavelet transform, is applied to detect the surface annual ring width distribution of the four sides of the selected sections. Finally, the pith location is estimated by comparing annual ring width distributions on the different surfaces, and assuming that annual rings are concentric circles with the pith in the centre. The proposed algorithm was applied to a total sample of 104 Norway spruce boards. Results indicate that optical scanners and the suggested automatic method allow for accurate detection of annual ring width and location of pith along boards. For a sample of boards with the pith located within the cross-section, a mean error of 2.6 mm and 3.2  mm in the depth and thickness direction, respectively, was obtained. For a sample of boards of which 60% with pith located outside the cross-section, a mean discrepancy between automatically and manually determined pith locations of 3.9 mm and 5.8 mm in depth and thickness direction, respectively, was obtained.

Knowledge of pith location is needed for modelling of sawn timber and for real time assessment of wood material in the wood working industry. However, the methods that are available and implemented in optical scanner today seldom meet customer requirements on accuracy and/or speed. In the present research data of greyscale images of the four longitudinal sides of board and a one-dimensional convolutional neural network were used to determine pith location along Norway spruce timber boards. A novel stochastic model was developed to generate thousands of virtual timber boards, with photo-realistic surfaces and known pith location, by which the network was trained before it was successfully applied to determine pith location along real boards.

In the woodworking industry, detection of annual rings and location of pith in relation to timber board cross sections, and how these properties vary in the longitudinal direction of boards, is relevant for many purposes such as assessment of shape stability and prediction of mechanical properties of timber. The current work aims at developing a fast, accurate and operationally simple deep learning-based algorithm for automatic detection of surface growth rings and pith location along knot-free clear wood sections of Norway spruce boards. First, individual surface growth rings that are visible along the four longitudinal sides of the scanned boards are detected using trained conditional generative adversarial networks (cGANs). Then, pith locations are determined, on the basis of the detected growth rings, by using a trained multilayer perceptron (MLP) artificial neural network. The proposed algorithm was solely based on raw images of board surfaces obtained from optical scanning and applied to a total of 104 Norway spruce boards with nominal dimensions of 45×145×4500mm³. The results show that optical scanners and the proposed automatic method allow for accurate and fast detection of individual surface growth rings and pith location along boards. For boards with the pith located within the cross section, median errors of 1.4 mm and 2.9 mm, in the x- and y-direction, respectively, were obtained. For a sample of boards with the pith located outside the board cross section in most positions along the board, the median discrepancy between automatically estimated and manually determined pith locations was 3.9 mm and 5.4 mm in the x- and y-direction, respectively.