An image processing method to recognize position of sawn boards within the log

Abstract

This paper addresses the problem of timber board positioning within the log where they were sawn from. The method takes as input log and board end cross-section images. It uses a two-step image matching method based on scale invariant feature transform (SIFT) and normalized correlation coefficient (NCC). In the first step, the scale factor and rotation angle of board end images are estimated from the board images that are correctly identified on the log end image by SIFT. Then, the accurate position of each board within the log end image is achieved by the NCC method. The method has been tested on 70 different log images and the 798 corresponding board images of various visual aspects and coming from three different species (Douglas fir, Norway spruce, and oak). The results fully demonstrate that the proposed method is not only rotation and scale invariant, but also has high accuracy properties.