Present trends, such as increasing costs and limited supplies of high quality logs, have been making hardwood lumber manufacturers increase efforts to maximize the utilization of their wood raw material. Lumber production is less than optimum because of the complexity of the grading rules, the decision process, operator skill, operator fatigue, and the precision of mechanical setworks. The optimization of lumber manufacturing must involve some degree of automation. This paper describes research aimed at developing a machine vision technology to drive automated processes in the hardwood forest products manufacturing industry. A prototype machine vision system has been designed to scan variable-size hardwood lumber for detecting features such as knots, holes, wane, stain, checks, and splits. The prototype system has also been designed to be general purpose so that a variety of different problems can be addressed in both primary and secondary hardwood manufacturing. INTRODUCTION Hardwood lumber manufacturers in the eastern U.S. produce more than 10 billion board feet (24,000 m3) of sawn hardwood lumber annually (Araman et al., 1992). Present trends such as increasing costs and limited supplies of high quality timber resources, have been making hardwood lumber manufacturers increase efforts to look for new ways to reduce costs and increase product value recovery. Presently, hardwood lumber production is less than optimum because of the complexity of the grading rules, the decision process, lThe authors are, respectively, Assistant Professor, Dept. of Wood Science and Forest Products, VP1S Graduate Research Assistant and Associate Professor, Spatial Data Analysis Laboratory, VPIS Research Forest Products Technologist and Project Leader, USDA Forest Service, Southeastern Forest Experiment Station, Brooks Forest Products Center, VPIS Conners et al. 1990b). Such a system is unique in that it can handle full-sized lumber at industrial speeds. Hence, industrial scale problems can be investigated. The system is being used to address a number of manufacturing
[1]
Philip A. Araman,et al.
Value of Defect Information in Automated Hardwood Edger and Trimmer Systems
,
1992
.
[2]
Richard W. Conners,et al.
A Multisensor Machine Vision System for Hardwood Defect Detection
,
1990
.
[3]
Richard W. Conners,et al.
A machine vision system forautomatically grading hardwood lumber
,
1992
.
[4]
Marshall S. White,et al.
CORY: A Computer Program for Determining Dimension Stock Yields
,
1989
.
[5]
Daniel L. Schmoldt,et al.
Machine Vision Systems for Processing Hardwood Lumber and Logs
,
1992
.
[6]
Richard W. Conners,et al.
Computer vision hardware system for automating rough mills of furniture plants
,
1990,
Defense, Security, and Sensing.
[7]
Robert J. Bush,et al.
Matching Your Hardwood Lumber to Market Needs
,
1990
.
[8]
Richard W. Conners,et al.
Automated computer grading of hardwood lumber
,
1988
.
[9]
Philip A. Araman,et al.
Hardwood Lumber Edger and Trimmer Training System
,
1992
.