Validation of automated hardwood lumber grading system

Grading is one of the most vital steps in the hardwood lumber manufacturing process. For over one hundred years, hardwood lumber in North America has been graded by specially trained lumber inspectors using the National Hardwood Lumber Association (NHLA) Rules for the Inspection of Hardwood Lumber....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computers and electronics in agriculture 2018-12, Vol.155, p.496-500
Hauptverfasser: Gazo, Rado, Wells, Logan, Krs, Vojtech, Benes, Bedrich
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Grading is one of the most vital steps in the hardwood lumber manufacturing process. For over one hundred years, hardwood lumber in North America has been graded by specially trained lumber inspectors using the National Hardwood Lumber Association (NHLA) Rules for the Inspection of Hardwood Lumber. With technology improving over time, the status quo of lumber grading is again being challenged. This paper outlines an automated lumber grading study using a Microtec Goldeneye 300 Multi-Sensor Quality Scanner™. The scanner is equipped with color cameras, dot-grid and profile lasers and an x-ray sensor to locate and classify defects at a speed of 980 linear feet per minute. The material studied was rough, kiln dried hardwood lumber of nine different commercial species. Over 1000 boards from each species were graded with the scanner and verified by a NHLA-trained human lumber inspector. This paper reviews the performance of the scanner and highlights its accuracy by species and individual grades within that species. Across the entire volume of boards scanned, the automated grading system was 99.50% on-value and 92.22% on-grade accurate.
ISSN:0168-1699
1872-7107
DOI:10.1016/j.compag.2018.06.041