Rapid Classification of Softwood and Hardwood by Near Infrared Spectroscopy of Wood Tangential Section

摘要

Due to the shortage of wood resource, manufacturers often use the wood raw materials mixed with softwood and hardwood. Rapid classification and ratio prediction of softwood and hardwood during processing is important to quality control. The feasibility on rapid classification of softwood and hardwood by near infrared spectroscopy (NIR) was investigated in this paper. The results showed that: 1) the classification accuracy of the calibration set samples was 100%. The correlation coefficient (r) between the NIR predicted and the true category variable value was 0.98 ~0.99 with low SEC of 0.06~0.11; 2) the classification accuracy to the unknown samples was 100%. It was suggested that near infrared spectroscopy can be used to rapidly and accurately classify softwood and hardwood samples.