Abstract
Wood discs from 67 pine and 79 spruce logs were collected from a forest clearing. Three different 24-bit red-green-blue (RGB) images were acquired from the radial surface of each disc. The first image contained bark, the second image was a mixture of bark and wood surface, and the third image consisted only of wood surface. The image texture was compressed into vectors of Fourier-transformed wavelet coefficients. These were assembled in matrices and analysed by principal component analysis (PCA) and partial least-squares projections to latent structures (PLS). Classification using Fourier-transformed wavelet scales showed that the wood species could be predicted with 90% accuracy. A thorough examination of this classification showed that the predicting power of these models was mostly due to wavelet scales that represented the mean value of each colour channel. The prediction accuracy that could be obtained from coefficients representing image texture was generally low. The use of grey-level co-occurrence matrices prior to the wavelet transformation showed, however, that it is possible to classify the wood species of pine and spruce with an accuracy approaching 100%.
References
Antonelli, A., Cocchi, M., Fava, P., Foca, G., Franchini, C.G., Ulrici, A. (2004) Automated evaluation of food colour by means of multivariate image analysis coupled to a wavelet-based classification algorithm. Anal. Chim. Acta515:3–13.10.1016/j.aca.2004.01.005Search in Google Scholar
Basset, O., Buquet, B., Abouelkaram, S., Delachartre, P., Culioli, J. (2000) Application of texture image analysis for the classification of bovine meat. Food Chem.69:437–445.10.1016/S0308-8146(00)00057-1Search in Google Scholar
Bharati, M.H., Liu, J.J., MacGregor J.F. (2004) Image texture analysis: methods and comparisons. Chemomet. Intell. Lab. Syst.72:57–71.10.1016/j.chemolab.2004.02.005Search in Google Scholar
Brunner, M., Eugster, R., Trenka, E., Bergamin-Strotz, L. (1996) FT-NIR spectroscopy and wood identification. Holzforschung50:130–134.10.1515/hfsg.1996.50.2.130Search in Google Scholar
Daubechies, I. Ten Lectures on Wavelets. SIAM, Philadelphia, 1992.10.1137/1.9781611970104Search in Google Scholar
Esbensen, K., Geladi, P. (1989) Strategy of multivariate image-analysis (MIA). Chemomet. Intell. Lab. Syst.7:67–86.10.1016/0169-7439(89)80112-1Search in Google Scholar
Funck, J.W., Zhong, Y., Butler, D.A., Brunner, C.C., Forrer, J.B. (2003). Image segmentation algorithms applied to wood defect detection. Comput. Electron. Agric.41:157–179.Search in Google Scholar
Geladi, P., Esbensen, K. (1991) Regression on multivariate images – Principal component regression for modeling, prediction and visual diagnostic tools. J. Chemomet.5:97–111.10.1002/cem.1180050206Search in Google Scholar
Geladi P., Kowalski, B.R. (1986) Partial least squares regression: A tutorial. Anal. Chim. Acta185:1–17.10.1016/0003-2670(86)80028-9Search in Google Scholar
Geladi, P., Isaksson, H., Lindqvist, L., Wold, S., Esbensen, K. (1989) Principal component analysis of multivariate images. Chemomet. Intell. Lab. Syst.5:209–220.10.1016/0169-7439(89)80049-8Search in Google Scholar
Gjerdrum, P., Warensjö, M., Nylinder, M. (2001) Classification of crook types for unbarked Norway spruce sawlogs by means of a 3D log scanner. Holz Roh Werkstoff59:374–379.10.1007/s001070100228Search in Google Scholar
Gonzalez R.C., Woods R.E. Digital Image Processing, 2nd ed. Prentice Hall, New Jersey, 2002.Search in Google Scholar
Hagman, P.O.G. (1993) Automatic quality sorting of Picea abies logs with a gamma-ray log scanner. Scand. J. For. Res.8:583–590.10.1080/02827589309382804Search in Google Scholar
Haralick, R.M., Shanmugam, K., Dinstein, I. (1973) Textural features for image classification. IEEE Trans. Syst. Man Cybernetics3:610–621.10.1109/TSMC.1973.4309314Search in Google Scholar
Jain, A.K., Mao, J.C., Mohiuddin, K.M. (1996) Artificial neural networks: A tutorial. Computer29:31–44.10.1109/2.485891Search in Google Scholar
Jordan, R., Feeney, F., Nesbitt, N., Evertsen, J.A. (1998) Classification of wood species by neural network analysis of ultrasonic signals. Ultrasonics36:219–222.10.1016/S0041-624X(97)00148-0Search in Google Scholar
Kvaal, K., Wold, J.P., Indahl, U.G., Baardseth, P., Næs, T. (1998) Multivariate feature extraction from textural images of bread. Chemomet. Intell. Lab. Syst.42:141–158.10.1016/S0169-7439(98)00017-3Search in Google Scholar
Lawrence, A.H. (1989) Rapid characterization of wood species by ion mobility spectrometry. J. Pulp Pap. Sci.15:J196–J199.Search in Google Scholar
Lewis, I.R., Daniel, N.W., Chaffin, N., Griffiths, P. (1994) Raman spectrometry and neural networks for the classification of wood types 1. Spectrochim. Acta A Mol. Spectrosc.50:1943–1958.10.1016/0584-8539(94)80207-6Search in Google Scholar
Lo, S.C.B., Li, H., Freedman, M.T. (2003) Optimization of wavelet decomposition for image compression and feature preservation. IEEE Trans. Med. Imaging22:1141–1151.10.1109/TMI.2003.816953Search in Google Scholar
Mäenpää, T., Pietikainen, M. (2004) Classification with colorand texture: jointly or separately? Pattern Recogn.37:1629–1640.Search in Google Scholar
Oja, J., Wallbäcks, L., Grundberg, S., Hägerdal, E., Grönlund, A. (2003) Automatic grading of Scots pine (Pinus sylvestris L.) sawlogs using an industrial X-ray log scanner. Comput. Electron. Agric.41:63–75.Search in Google Scholar
Thygesen, L.G., Lundqvist, S.O. (2000) NIR measurement of moisture content in wood under unstable temperature conditions. Part 1. Thermal effects in near infrared spectra of wood. J. Near Infrared Spectrosc.8:183–189.Search in Google Scholar
Trygg, J., Wold, S. (2002) Orthogonal projections to latent structures, O-PLS. J. Chemomet.16:119–128.10.1002/cem.695Search in Google Scholar
Van de Wouwer, G., Scheunders, P., Livens, S., Van Dyck, D. (1999) Wavelet correlation signatures for color texture characterization. Pattern Recogn.32:443–451.10.1016/S0031-3203(98)00035-1Search in Google Scholar
Wettimuny, R., Penumadu, D. (2004) Application of Fourier analysis to digital imaging for particle shape analysis. J. Comp. Civil Eng.18:2–9.10.1061/(ASCE)0887-3801(2004)18:1(2)Search in Google Scholar
Wold, S. (1978) Cross-validatory estimation of the number of components in factor and principal components models. Technometrics20:397–405.10.1080/00401706.1978.10489693Search in Google Scholar
Wold S., Esbensen, K., Geladi, P. (1987) Principal component analysis. Chemomet. Intell. Lab. Syst.2:37–52.10.1016/0169-7439(87)80084-9Search in Google Scholar
Wold, S., Antti, H., Lindgren, F., Öhman, J. (1998) Orthogonal signal correction of near-infrared spectra. Chemomet. Intell. Lab. Syst.44:175–185.10.1016/S0169-7439(98)00109-9Search in Google Scholar
©2005 by Walter de Gruyter Berlin New York
