Determination of pith location along Norway spruce timber boards using one dimensional convolutional neural networks trained on virtual timber boards

Abstract

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.