|
Automated Detection of Defects in Hardwood Logs |
|
|
|
Abstract. Before noninvasive scanning, e.g.,
computed tomography (CT), can be applied in industrial operations, we need a
procedure that automatically interprets scan information so that it can
provide the saw operator with the information necessary to make proper
sawing decisions. Our current approach to automatically label features in CT
images of hardwood logs classifies each pixel individually using a
back-propagation artificial neural network (ANN) and feature vectors that
include a small, local neighborhood of pixels and the distance of the target
pixel to the center of the log. Initially, this ANN was able to classify
clear wood, bark, decay, knots, and voids in CT images of two species of oak
with 95% pixel-wise accuracy. Recently we have investigated other ANN
classifiers, comparing 2-D versus 3-D neighborhoods and species-dependent
(single species) versus species-independent (multiple species) classifiers
using oak (Quercus rubra, L. and Q. nigra, L.), yellow poplar
(Liriodendron tulipifera, L.), and black cherry (Prunus serotina,
L.) CT images. When considered individually, the resulting species-dependent
classifiers yield similar levels of accuracy (96-98%). 3-D neighborhoods
work better for multiple-species classifiers and 2-D is better for
single-species. Classifiers combining yellow poplar and cherry data
misclassify many pixels belonging to splits as clear wood, resulting in
lower classification rates. If yellow poplar is not paired with cherry,
however, there is no statistical difference in accuracy between single- and
multiple-species classifiers.
Daniel L. Schmoldt and A. Lynn Abbott (VA Tech)
Current and Future Work
Last Modified:
06/13/07
|
