An image processing algorithm for detection and analysis of slicing checks

Abstract

In this paper, a new method of measuring slicing checks for flat-sliced veneers was evaluated. The method is based on image analysis of veneer cross-sections, having highlighted the slicing checks using surface staining. The segmentation of the checks consists of global thresholding followed by some morphological operations. The outputs of the algorithm are check depth ratio and check frequency. The method was tested on flat-sliced oak (Quercus robur L. and Quercus petraea (Matt). Liebl.) veneers of different thicknesses (1.5, 2.5, 3.5 and 4.5\xa0mm). Two distinct wood qualities and two different cutting directions (lengthwise-sliced and plain-sliced veneers) were evaluated. The algorithm performance resulted in an overall accuracy of 85% enabling an accessible method for relatively fast and accurate measurements of slicing check characteristics in lamella cross-sections. Regression analysis indicated a lack of fixed bias but the presence of proportional bias with the presented method. Check measurements indicate that by varying cutting parameters, it is possible to achieve desired check characteristics independent of slicing thickness. The semi-automated slicing check detection method could benefit further research and optimisation of the slicing process parameters and pave the way towards industrial quality control of slicing checks. The intended area of application is veneer-laminated products for interior use with the focus on veneered wood flooring.