Automatic detection of annual rings and pith location along Norway spruce timber boards using conditional adversarial networks

Abstract

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 $$45\times 145\times 4500\,\hbox {mm}^{3}$$ 45 × 145 × 4500 mm 3 . 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.

Computer Vision-Based Wood Identification: A Review

“…Generative adversarial networks can produce highly realistic images using CNNs in an unsupervised manner [144]. Their application extends to multiple fields of scientific research, but they remain poorly explored in wood sciences [145][146][147].…”

Performance of timber board models for prediction of local bending stiffness and strength - with application on Douglas fir sawn timber

“…Habite et al (2020) presented a method to automatically determine location of pith in relation to board cross sections, based on optical scanning of the four longitudinal surfaces of boards and identification of annular ring pattern on images of the surfaces. Faster and more robust methods, based on optical scanning of longitudinal board surfaces in combination with machine learning, were developed by Habite et al (2021) and in particular Habite et al (2022). Thus, it is possible to determine pith location in production speed at sawmills and to utilize this in models of boards.…”