Authors: Jukka Koskinen, Tapio Vaarala, Tapio Heikkilä, Teemu Rahkola
Abstract: In this paper, we present a system for real-time
quality inspection of wooden parts. The quality inspection system
was developed for classifying wooden parts in an application
with automated robotic handling operations. An essential feature
is the detection of different grain patterns from the part surface.
The quality inspection consists of CMOS camera imaging,
texture analysis of images, and feature-based classification for
evaluating the surface quality. The features are extracted from
blobs and the classification algorithm relies on support vector
machines. Based on our test results, the reliability of the
classification is at a sufficient level.
Keywords: machine vision, support vector machine, wood