Comparison between neural networks and partial least squares for intra-growth ring wood density measurement with hyperspectral imaging

In this paper, a procedure for transforming hyperspectral imaging information into intra-growth ring wood densities is presented. Particular focus was given to comparing the neural network and Partial Least Squares Regression (PLSR) processing methods. The hyperspectral measurements were performed in a wavelength range of 380-1028nm, with a spatial separation of 79@mm. The study employed 34 samples from the same number of Pinus pinea tree samples. Density values were analyzed at a total of 34,093 positions in the samples. For neural networks, the mean absolute percentage error (MAPE) and standard deviation of absolute percentage error (StdAPE) values were 6.49% and 5.43%, respectively. For the PLSR method the MAPE and StdAPE were 6.87% and 5.70%, respectively. The neural networks allow reducing the percentage of sample positions with large errors. The proposed method for density measurement can be used for dendrochronology and dendroclimatology.

[1]  M. Schwanninger,et al.  A common near infrared—based partial least squares regression model for the prediction of wood density of Pinus pinaster and Larix × eurolepis , 2010, Wood Science and Technology.

[2]  H. Polge.  Fifteen years of wood radiation densitometry , 1978, Wood Science and Technology.

[3]  J. Louzada,et al.  The heritability of wood density components in Pinus pinaster Ait. and the implications for tree breeding , 2002 .

[4]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[5]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[6]  Colm P. O'Donnell,et al.  Hyperspectral imaging – an emerging process analytical tool for food quality and safety control , 2007 .

[7]  Richard F. Daniels,et al.  Comparison of Pinus taeda L. whole-tree wood property calibrations using diffuse reflectance near infrared spectra obtained using a variety of sampling options , 2008, Wood Science and Technology.

[8]  Robert Evans,et al.  Estimation of air-dry density of increment cores by near infrared spectroscopy , 2003 .

[9]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[10]  P. Hoffmeyer,et al.  Evaluation of density and strength of Norway spruce wood by near infrared reflectance spectroscopy , 2007, Holz als Roh- und Werkstoff.

[11]  Robert Evans,et al.  Estimation of Eucalyptus delegatensis wood properties by near infrared spectroscopy , 2001 .

[12]  Art Springsteen.  Standards for the measurement of diffuse reflectance – an overview of available materials and measurement laboratories , 1999 .

[13]  Richard F. Daniels,et al.  Nondestructive estimation of Pinus taeda L. wood properties for samples from a wide range of sites in Georgia , 2005 .

[14]  A. Clark,et al.  High resolution scanning of radial strips cut from increment cores by near infrared spectroscopy , 2007 .

[15]  Robert Evans,et al.  APPLICATION OF NEAR INFRARED SPECTROSCOPY TO THE EXTRACTED WOOD OF A DIVERSE RANGE OF SPECIES , 2003 .

[16]  Lisbeth G. Thygesen,et al.  Determination of Dry Matter Content and Basic Density of Norway Spruce by near Infrared Reflectance and Transmittance Spectroscopy , 1994 .

[17]  Shuijuan Feng,et al.  Measurement of yogurt internal quality through using Vis/NIR spectroscopy , 2007 .

[18]  Robert Evans,et al.  APPLICATION OF NEAR INFRARED SPECTROSCOPY TO A DIVERSE RANGE OF SPECIES DEMONSTRATING WIDE DENSITY AND STIFFNESS VARIATION , 2001 .

[19]  Satoru Tsuchikawa,et al.  A Review of Recent Near Infrared Research for Wood and Paper , 2007 .

[20]  Leslie H. Groom,et al.  Ability of near infrared spectroscopy to monitor air-dry density distribution and variation of wood , 2005 .

[21]  L. Schimleck,et al.  Estimation ofPinus radiata D. Don clear wood properties by near-infrared spectroscopy , 2002, Journal of Wood Science.

[22]  Laurence R. Schimleck,et al.  Kernel regression methods for the prediction of wood properties of Pinus taeda using near infrared spectroscopy , 2010, Wood Science and Technology.