Classification of Wood Surface Features by Spectral Reflectance
Keywords:
Principal-component analysis, discriminant analysis, classification, spectral reflectance, color, Douglas-fir, woodAbstract
A database of spectral-reflectance curves of Douglas-fir veneer surface features is presented and analyzed via principal-component analysis. The paper describes how such analysis can be used to model and classify the spectral-reflectance curves by feature type. For modeling (curve-reconstruction) purposes, three principal components were sufficient by most criteria. For classification purposes, seven principal components achieved classification accuracies (with quadratic discriminant analysis) on the order of 99%, comparable to the accuracies achieved with the raw spectral data. The best seven principal components were not those associated with the largest variation in the data. This paper suggests how comparable classification accuracies might be achieved in a system operating at production speeds in a mill.References
Brunner, C. C., G. B. Shaw, D. A. Butler, and J. W. Funck. 1990. Using color in machine vision systems for wood processing. Wood Fiber Sci. 22(4):413-428.nBrunner, C. C., A. G. Maristany, D. A. Butler, D. VanLeeuwen, and J. W. Funck. 1992. An evaluation of color spaces for detecting defects in Douglas-fir vencer. Ind. Metrol. 2:169-184.nBuchsbaum, G., and A. Gottschalk. 1984. Chromaticity coordinates of frequency-limited functions. J. Opt. Soc. Am. A 8:885-887.nButler, D. A., C. C. Brunner, and J. W. Funck. 1989. A dual-threshold image sweep-and-mark algorithm for defect detection in veneer. Forest Prod. J. 39(5):25-28.nCochran, R. N., and F. H. Horne. 1977. Statistically weighted principal component analysis of rapid scanning wavelength kinetics experiments. Anal. Chem. 49: 846-853.nCohen, J. 1964. Dependency of the spectral reflectance curves of the Munsell color chips. Psychon. Sci. 1:369-370.nConners, R. W., C. W. McMillin, and C. N. NG. 1985. The utility of color information in the location and identification of defects in surfaced hardwood lumber. Pages XVIII-1 to XVIII-33 in Proc., First International Conference on Scanning Technology in Sawmilling. Miller-Freeman Publications, San Francisco, CA.nFlury, B. 1988. Common principal components and related multivariate models. John Wiley and Sons, New York, NY.nHabbema, J. D. F., and J. Hermans. 1977. Selection of variables in discriminant analysis by F-statistic and error rate. Technometrics 19:487-493.nHealey, G. 1989. Using color for geometry-insensitive segmentation. J. Opt. Soc. Am. A 6:920-937.nHealey, G., and T. O. Binford. 1987. The role and use of color in a general vision system. Pages 599-613 in Proc., ARPA Image Understanding Workshop, DARPA. University of Southern California, Los Angeles, CA.nHoogerbrugge, R., S. J. Willig, and P. G. Kistemaker. 1983. Discriminant analysis by double stage principal-component analysis. Anal. Chem. 55:1710-1712.nHoyt, C. C. 1995. Toward higher res, lower cost quality color, and multispectral imaging. Adv. Imaging 10(4): 53-55.nHunter, R. S., and R. W. Harold. 1987. The measurement of appearance. 2nd ed. John Wiley and Sons, New York, NY.nKanade, T., and K. Ikeuchi. 1991. Introduction to the special issue on physical modeling in computer vision. IEEE Trans. Pattern Anal. Mach. Intell. PAMI. 13:609-610.nKlapstein, K. D., F. L. Weichman, W. N. Bauer, and D. J. Kenway. 1989. Optical characteristics of wood stains and rot. Appl. Opt. 28(20):4450-4452.nKrzanowski, W. J. 1979. Between-groups comparison of principal components. J. Am. Stat. Assoc. 74:703-707.nKrzanowski, W. J. 1984. Principal-component analysis in the presence of group structure. Appl. Stat. 33:164-168.nKrzanowski, W. J. 1987, Cross-validation in principal-component analysis. Biometrics 43:575-584.nLebow, P. K. 1992. Estimation of discriminant analysis error rate for high dimensional data. Doctoral thesis. Department of Statistics, Oregon State University, Corvallis, OR.nMacAdam, D. L. 1981. Color measurement: Theme and variations. Springer-Verlag, Berlin, Germany.nMaloney, L. T. 1986. Evaluation of linear models of surface spectral reflectance with small numbers of parameters. J. Opt. Soc. Am. A 3:1673-1683.nManly, B. F. J., and J. C. W. Rayner. 1987. The comparison of sample covariance matrices using likelihood ratio tests. Biometrika 74:841-847.nMardia, K. V., J. T. Kent, and J. M. Bibby. 1979. Multivariate analysis. Academic Press, Orlando, FL.nMaristany, A. G., P. K. Lebow, C. C. Brunner. 1994. Application of the dichromatic reflection model to wood. Wood Fiber Sci. 26(2):249-258.nMaristany, A. G., D. A. Butler, C. C. Brunner, and J. W. Funck. 1991. Exploiting local color information for defect detection on Douglas-fir veneer. Pages 1-7 in Proc., Fourth International Conference on Scanning Technology in Sawmilling. Miller-Freeman Publications, San Francisco, CA.nMaristany, A. G., P. K. Lebow, C. C. Brunner, D. A. Butler, and J. W. Funck. 1993. Classifying wood-surface features using dichromatic reflection. Pages 56-64 in J. A. DeShazer and G. E. Meyers, eds. Optics in agriculture and forestry. Proc., SPIE 1836. SPIE-The International Society for Optical Engineering, Bellingham, WA.nMatthews, P. C., and B. H. Beech. 1976. Method and apparatus for detecting timber defects. U.S. Patent No. 3,976,384.nParkkinen, J. P. S., and T. Jaaskelainen. 1987. Color representation using statistical pattern recognition. Appl. Opt. 26:4240-4245.nParkkinen, J. P. S., J. Hallikainen, and T. Jaaskelainen. 1989. Characteristic spectra of Munsell colors. J. Opt. Soc. Am. A 6:318-322.nPhelps, J. E., E. A. McGinnes, Jr., H. E. Garett, and G. S. Cox. 1983. Growth-quality evaluation of black walnut wood. Part II — Color analyses of veneer produced on different sites. Wood Fiber Sci. 15(2): 177-185.nRao, C. R. 1964. The use and interpretation of principal-component analysis in applied research. Sankhya A. 26: 329-358.nRozett, R. W., and E. M. Petersen. 1976. Classification of compounds by the factor analysis of their mass spectra. Anal. Chem. 48:817-825.nSeber, G. A. F. 1984. Multivariate observations. John Wiley and Sons, New York, NY.nSimonds, J. L. 1963. Application of characteristic vector analysis to photographic and optical response data. J. Opt. Soc. Am. 53:968-974.nSnapinn, S. M., and J. D. Knoke. 1988. Bootstrapped and smoothed classification error rate estimators. Commun. Stat. — Simul. Comput. 17:1135-1153.nSoest, J. 1984. Optical scanning technique for defect detection. Scanning technology for the eighties. Spec. Publ. No. SP-21:120-123. Forintek Canada Corp., Vancouver, BC, Canada.nSoest, J., and P. C. Matthews. 1985. Laser Scanning technique for defect detection. Pages XVII-1 to XVII-4 in Proc. First International Conference on Scanning Technology in Sawmilling. Miller Freeman Publications, San Francisco, CA.nStewart, G. W. 1987. Collinearity and least squares regression. Stat. Sci. 2(1):68-100.nStiles, W. S., and G. Wyszecki. 1962. Counting metameric object colors. J. Opt. Soc. Am. 52:58-75.nStiles, W. S., G. Wyszecki. and N. Ohta. 1977. Counting metameric object-color stimuli using frequency-limited spectral reflectance functions. J. Opt. Soc. Am. 67:779-784.nTominaga, S., and B. A. Wandell. 1989. Standard surface-reflectance model and illuminant estimation. J. Opt. Soc. Am. A 6:576-584.nTrussell, H. J. 1994. Personal communication. Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC.nVora, P. L., and H. J. Trussell. 1993. A mathematical method for designing a set of colour scanning filters. Pages 322-329 in J. Bares, ed. Color hard copy and graphics arts II. Proc., SPIE 1912. SPIE-The International Society for Optical Engineering, Bellingham, WA.nVrhel, M. J., and H. J. Trussell. 1993. Optimal scanning filters using spectral reflectance information. Pages 404-411 in B. E. Rogowitz and J. P. Allebach, eds. Human vision, visual processing, and digital display IV. Proc., SPIE 1913. SPIE—The International Society for Optical Engineering, Bellingham, WA.nWold, S. 1978. Cross-validatory estimation of the number of components in factor and principal components models. Technometrics 20:397-405.nYoung, R. A. 1986. Principal-component analysis of macaque lateral geniculate nucleus chromatic data. J. Opt. Soc. Am. A 3:1735-1742.n
Downloads
Published
Issue
Section
License
The copyright of an article published in Wood and Fiber Science is transferred to the Society of Wood Science and Technology (for U. S. Government employees: to the extent transferable), effective if and when the article is accepted for publication. This transfer grants the Society of Wood Science and Technology permission to republish all or any part of the article in any form, e.g., reprints for sale, microfiche, proceedings, etc. However, the authors reserve the following as set forth in the Copyright Law:
1. All proprietary rights other than copyright, such as patent rights.
2. The right to grant or refuse permission to third parties to republish all or part of the article or translations thereof. In the case of whole articles, such third parties must obtain Society of Wood Science and Technology written permission as well. However, the Society may grant rights with respect to Journal issues as a whole.
3. The right to use all or part of this article in future works of their own, such as lectures, press releases, reviews, text books, or reprint books.
