Defect detection performance of automated hardwood lumber grading system

Abstract

This paper describes the abilities of the Microtec Goldeneye 300 Multi-Sensor Quality Scanner™ to recognize and identify defects for purpose of grading kiln dried, rough, hardwood lumber using the GradeView™ grading algorithm. The overall accuracy of the automated grading system was found to be 92.22% on grade and 99.50% on value as defined by the National Hardwood Lumber Association sales code, well within industry standards. We also discuss the small number of boards that were graded incorrectly by the system and specifically how the multi sensor scanner detects various lumber defects. This scanner has six different types of sensors-color cameras, black and white cameras, profile cameras, line lasers, dot lasers and an X-ray that work together to provide accurate detail for lumber grading.