Wood species identification using spectral reflectance feature and optimal illumination radian design

Abstract

We developed a novel wood recognition scheme based on wood surface spectral features that aimed to solve three problems. First was elimination of noise in some bands of wood spectral reflection curves. Second was improvement of wood feature selection based on analysis of wood spectral data. The wood spectral band is 350–2500 nm, a 2150D vector with a spectral sampling interval of 1 nm. We developed a feature selection procedure and a filtering procedure by solving the eigenvalues of the dispersion matrix. Third, we optimized the design for the indoor radian’s mounting height. We used a genetic algorithm to solve the optimal radian’s height so that the spectral reflection curves had the best classification information for wood species. Experiments on fivecommon wood species in northeast China showed overall recognition accuracy >95 % at optimal recognition velocity.

Keywords

Wood species identification / Feature selection / Radian / Genetic algorithm / Spectral analysis

References

[1] Chen GS, Zhao P. Dynamic wood slice recognition using image blur information. Sens Actuators A, 2012, 176: 27-33.

[2] Lavine BK, Davidson CE, Moores AJ, Griffiths PR. Raman spectroscopy and genetic algorithms for the classification of wood types. Appl Spectrosc, 2001, 55(8): 960-966.

[3] Moore AK, Owen NL. Infrared spectroscopic studies of solid wood. Appl Spectrosc Rev, 2001, 36(1): 65-86.

[4] Nakamura M, Masuda M, Shinohara K. Multiresolutional image analysis of wood and other materials. J Wood Sci, 1999, 45(1): 10-18.

[5] Orton CR, Parkinson DY, Evans PD, Owen NL. Fourier transform infrared studies of heterogeneity, photodegradation, and lignin/hemicellulose ratios within hardwoods and softwoods. Appl Spectrosc, 2004, 58(11): 1265-1271.

[6] Packianather MS, Drake PR. Neural networks for classifying images of wood veneer. Int J Adv Manuf Technol, 2000, 16(6): 424-433.

[7] Phelps JE, Mcginnes EA. Growth-quality evaluation of black walnut wood, Part 2—color analysis of veneer produced on different sites. Wood Fiber Sci, 1983, 15(2): 177-185.

[8] Piuri V, Scotti F. Design of an automatic wood types classification system by using fluorescence spectra. IEEE Trans SMC C, 2010, 40(3): 358-366.

[9] Qiang W, Ying HC, Brigitte L, Shu YZ. Identification of selected internal wood characteristics in computed tomography images of black spruce: a comparison study. J Wood Sci, 2009, 55(3): 175-180.

[10] Tsuchikawa S, Hirashima Y, Sasaki Y, Ando K. Near-infrared spectroscopic study of the physical and mechanical properties of wood with meso- and micro-scale anatomical observation. Appl Spectrosc, 2005, 59(1): 86-93.