Optimization potential for perception-oriented appearance classification by simulated sawing of computed tomography-scanned logs of Norway spruce

Abstract

Wood, as a natural material, has favourable properties in both technical and aesthetic aspects. Due to its inherent variability, production of high-quality sawn timber demands adequate control of log conversion, which is feasible with computed tomography (CT) log scanning. Existing appearance grading rules for sawn timber might not fully reflect people's visual perception of wood surfaces, and therefore, an alternative, more perception-oriented appearance classification could be beneficial. An appearance classification of sawn timber based on partial least squares discriminant analysis (PLS-DA) of knot-pattern variables was developed and tested. Knot-pattern variables derived from images of board faces were used in training PLS-DA models against an initial classification of the board faces previously established by aid of cluster analysis. Virtual board faces obtained from simulated breakdown of 57 CT-scanned Norway spruce logs were graded according to the developed classification. Visual assessment of the grading results indicated that the classification was largely consistent with human perception of board appearance. An initial estimation of the potential to optimize log rotation, based on CT data, for the established appearance grades was derived from the simulations. Considerable potential to increase the yield of a desired appearance grade, compared to conventional log positioning, was observed.

Lateral forces determine dimensional accuracy of the narrow-kerf sawing of wood

“…This, in combination with the ever-increasing consumption of wood because of a growing population, can lead in the coming years to the lack of a positive balance between the annual volumetric growth and consumption of wood 3 . Projected and actual scarcity of the raw material (logs) availability, increasing competition on the international market, combined with significant and ever-growing production costs compel wood processing plants to dramatically modernize their technologies 4 , 5 . An important innovation toward increasing environmental and economic sustainability of timber production is to reduce the volume of wood residues by minimizing the sawing kerf.…”

Maximizing value yield in wood industry through flexible sawing and product grading based on wane and log shape

“…For the live and cant sawing schemes, the CP assignment decision is done using two approaches. In the first approach, the CPs are selected based on the logs' top-end or butt-end diameters, see for example Nordmark and Oja (2004), Fredriksson (2014), Breinig et al (2015) and Ah Shenga et al (2016). In the second approach, the log is examined for all or a subset of CPs to select the one that results in a higher yield, see for example Pereira and Usenius (2006), Thomas (2012), Riesco Muñoz et al (2013, Ursella et al (2018) and Khaloian Sarnaghi et al (2020).…”

Product-adapted grading of Scots pine sawn timber by an industrial CT-scanner using a visually-trained machine-learning method

“…Relatable to the studies Lycken andOja (2006), Berglund et al (2015), Olofsson et al (2019a), andBreinig et al (2015b) performed cluster analysis and classification of floor boards according to their subjective visual characteristics, showing the possibility to use a set of knot descriptive variables to group floor boards into homogeneous clusters with significant differences. Furthermore, in a continuation study, Breinig et al (2015a) used simulated sawing of CT-scanned logs to optimise the rotational angle of the logs to yield the most number of floor boards of cluster-grades defined as in the previous study. Both studies showed the potential to use machine learning methods, in particular PLS, to appearance grade sawn timber by their holistic-subjective appearance.…”