LUMBER GRADING Spatial WITH A COMPUTER

Over the past few years significant progress has been made in developing a computer vision system for locating and identifying defects on surfaced hardwood lumber. Unfortunately, until September of 1988 little research had gone into developing methods for analyzing rough lumber. This task is arguably more complex than the analysis of surfaced lumber. The prime motivation for developing such a system is the goal of creating an automatic grading system. This paper reports progress that has been made in developing a vision system for locating and identifying defects on rough lumber. It will point out some problems that are unique to the analysis of rough lumber and will report studies aimed at addressing these problems. INTRODUCTION. Over the last few years significant progress has been made in developing a computer vision system for locating and identifying defects on surfaced hardwood lumber [1-4]. The motivation for this research is to create the “eyes” for an automatic cutup system to be used in rough mills of hardwood furniture, cabinet, dimension and fixture plants. The research has progressed to the extent that a prototype system for scanning full length sixteen foot boards is currently being designed and will be built in the very near future. (Note that this same prototype will be able to scan rough lumber as well.)