Using Color in Machine Vision Systems for Wood Processing
Keywords:
Optical scanning, machine vision, automation, spectral reflectance, color modelsAbstract
Color information, already shown to be valuable in distinguishing wood surface features, should prove especially useful for future applications of machine vision in the wood products industry. This review provides investigators interested in such applications with the information necessary for understanding the benefits-and associated difficulties-of using color. Various standard color-measurement systems ("color spaces") are discussed. No one system has been completely successful, at least partly because simple physical measurements are difficult to correlate with a human observer's complex perception of color. Color video camera systems, designed with human viewers in mind, have the potential for machine vision applications, but certain system "features" (white balance, gamma or contour correction) could cause problems. Future applications, including detecting and classifying hard-to-identify defects and matching colors of wood components, will require careful choice of lighting geometry and source, camera system, and color space for the purpose at hand.References
Aus, H. M., H. Harms, M. Haucke, B. Gerlach, A. Kriete, and S. Thieme. 1983. Computer color vision. Pages 225-229 in Intelligent Robots: Proceedings, 3rd International Conference on Robot Vision and Sensory Controls, Cambridge, MA. SPIE Vol. 449, Bellingham, WA.nBeckwith, J. R., III. 1979. Theory and practice of hardwood color measurement. Wood Sci. 11:169-175.nBillmeyer, F. W., Jr., and M. Saltzman. 1981. Principles of color technology. John Wiley & Sons, New York.nBrauner, A. B., and W. E. Loos. 1968. Color changes in black walnut as a function of temperature, time, and two moisture conditions. Forest Prod. J. 18(5):29-34.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.nConners, R. W., P. Klinkachorn, C. W. McMillin, J. P. Franklin, and C. N. Ng. 1987. A Computer vision system for grading hardwood lumber. Pages XV-1 to XV-7 in Proceedings, 2nd International Conference on Scanning Technology in Sawmilling. Miller Freeman, San Francisco, CA.nConners, R. W., C. W. McMillin, K. Lin, and R. E. Vasques-Espinosa. 1983. Identifying and locating surface defects in wood: Part of an automated lumber processing system. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-5(6):573-583.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 Proceedings, 1st International Conference on Scanning Technology in Sawmilling. Miller Freeman, San Francisco, CA.nConners, R. W., C. W. McMillin, and R. E. Vasques-Espinosa. 1984a. A prototype software system for locating and identifying surface defects in wood. Proceedings, 7th International Conference on Pattern Recognition, Montreal, Canada 7(1):416-419.nConners, R. W., C. W. McMillin, and R. E. Vasques-Espinosa. 1984b. A prototype software system for locating and identifying surface defects in wood. Scanning technology for the eighties. Spec. Publ. No. SP-21:107-114. Forintek Canada Corp., Vancouver, B.C., Canada.nDaley, W., R. Millet, C. Soulakos, and C. Thompson. 1988. A novel application: Machine vision inspection, grading and parts identification of chicken parts. Pages 13-33 to 13-49 in Robots 12 and Vision '88 Conference Proceedings, vol. 2. Society of Manufacturing Engineers, Dearborn, MI.nEstes, J. E., E. J. Hajic, and L. R. Tinney. 1983. Fundamentals of image analysis: Analysis of visible and thermal infrared data. Pages 987-1124 in Manual of remote sensing, vol. 1: Theory, instruments and techniques. American Society of Photogrammetry, Falls Church, VA.nFoley, J. D., and A. Van Dam. 1983. Fundamentals of interactive computer graphics. Addison-Wesley, Reading, MA.nForrer, J. B., D. A. Butler, C. C. Brunner, and J. W. Funck. 1989. Image sweep-and-mark algorithms: Part 2: Performance evaluations. Forest Prod. J. 39(1):39-42.nForrer, J. B., D. A. Butler, J. W. Funck, and C. C. Brunner. 1988. Image sweep-and-mark algorithms: Part 1: Basic algorithms. Forest Prod. J. 38(11/12):75-79.nFukada, Y. 1980. Spatial clustering procedures for region analysis. Pattern Recognition 12:395-403.nFunck, J. W., D. A. Butler, C. C. Brunner, and G. B. Shaw. 1987. Evaluation of image analysis routines for defect scanning on wood surfaces. Pages XIII-1 to XIII-19 in Proceedings, 2nd International Conference on Scanning Technology in Sawmilling. Miller Freeman, San Francisco, CA.nGray, V. R. 1961. The colour of wood and its changes. Res. Rep. C/RR/10. Timber Development Association Ltd., St. John's Rd., Tylers Green, High Wycombe, Buckinghamshire, England.nHiller, C. H., F. Freese, and D. M. Smith. 1972. Relationships in black walnut heartwood between color and other physical and anatomical characteristics. Wood Fiber 4:38-42.nHunter, R. S., and R. W. Harold. 1987. The measurement of appearance. John Wiley & Sons, New York.nIto, T. 1976. Pattern classification by color effect method. Pages 833-837 in 3rd International Conference on Pattern Recognition. IEEE Computer Society, Los Angeles, CA.nKeil, R. E. 1983. Machine vision with color detection. Pages 50-512 in Intelligent Robots: Proceedings, 3rd International Conference on Robot Vision and Sensory Controls, Cambridge, MA. SPIE Vol. 449, Bellingham, WA.nKelly, R. B., and W. Faedo. 1985. A first look into color vision. Pages 96-103 in Intelligent Robots and Computer Vision: Proceedings, International Society for Optical Engineers. SPIE Vol. 579, Bellingham, WA.nLakatosh, B. K. 1966. (Translated 1970). Defectoscopy of wood. Indian National Scientific Documentation Center, New Delhi.nLee, R. L. 1988. Colorimetric calibration of a video digitizing system: Algorithm and application. COLOR Res. Appl. 13(3): 180-186.nLevine, M. D. 1985. Vision in man and machine. McGraw-Hill, New York.nLoos, W. E., and W. A. Coppock. 1964. Measuring wood color with precision. Forest Prod. J. 14(2):85-86.nMatthews, P. C. 1987. Wood, light and objective scanning. Pages XI-1 to XI-13 in Proceedings, 2nd International Conference on Scanning Technology in Sawmilling. Miller Freeman, San Francisco, CA.nMcGinnes, E. A., Jr. 1975. Influence of incandescent and fluorescent light on the color of unfinished heartwood of black walnut and eastern redcedar. Wood Sci. 7:270-279.nMcGinnes, E. A., Jr., and T. W. Dingeldein. 1971. Effect of light, extraction, and storage on color and tackiness of clear-finished eastern redcedar. Forest Prod. J. 21(1):53-60.nMcGinnes, E. A., Jr., and P. K. Melcarek. 1976. Equipment for studying the color characteristics of wood at the cellular level. Wood Sci. 9:46-50.nMoon, P., and D. E. Spencer. 1948. The color of unstained wood. J. Opt. Soc. Am. 38:405-408.nMoslemi, A. A. 1969. Quantitative color characterization for loblolly pine veneer. Wood Sci. 2:61-64.nMunsell Color Company. 1929. Munsell book of color, Standard ed. Baltimore, MD.nNakamura, G., and H. Tackachio. 1960. Reflection of light and roughness on sanded surfaces of wood. J. Jpn. Wood Res. Soc. 6:237-242.nNelson, N. D., R. R. Maeglin, and H. E. Wahlgren. 1969. Relationship of black walnut wood color to soil properties and site. Wood Fiber 1:29-37.nOhlander, R. 1975. Analysis of natural color scenes. Ph.D. thesis, Department of Computer Science, Carnegie-Mellon University, Pittsburgh, PA.nOhta, Y. 1985. Knowledge-based interpretation of outdoor natural color scenes. Pitman, Marshfield, MA.nOhta, Y., T. Kanade, and T. Sakai. 1980. Color information for region segmentation. Comput. Graphics Image Process. 13:222-241.nPhelps, J. E., and E. A. McGinnes, Jr. 1983. Growth-quality evaluation of black walnut wood. Part II-An anatomical study of color characteristics of black walnut veneer. Wood Fiber Sci. 15:212-218.nPhelps, J. E., E. A. McGinnes, Jr., H. E. Garrett, and G. S. Cox. 1983. Growth-quality evaluation of black walnut wood. Part II-Color analysis of veneer produced on different sites. Wood Fiber Sci. 15:177-185.nPointer, M. R. 1981. A comparison of the CIE 1976 color spaces. COLOR Res. Appl. 6(2):108-117.nPritchard, D. H. 1977. U.S. color television fundamentals-A review. IEEE Trans. Consum. Electron. CE-23(4):467-478.nResch, H., E. T. Choong, and H. H. Smith. 1968. Sorting incense cedar types for drying. Forest Prod. J. 18(4):40-44.nRink, G. 1987. Heartwood color and quantity variation in a young black walnut progeny test. Wood Fiber Sci. 19:93-100.nRomanik, P. B. 1988. High-speed color image analysis for machine vision. Pages 13-17 to 13-31 in Robots 12 and Vision '88 Conference Proceedings, vol. 2. Society of Manufacturing Engineers, Dearborn, MI.nSchowengerdt, R. A. 1983. Techniques for image processing and classification in remote sensing. Academic Press, New York.nShearer, S. A., and R. G. Holmes. 1987. Plant identification using color co-occurrence matrices. Paper No. 87-1534. American Society of Agricultural Engineers, St. Joseph, MI.nShibamoto, T., Y. Inoue, and Y. Kenjo. 1961a. Studies on water-borne wood preservatives XVII: Color change of treated wood by weathering procedure. J. Jpn. Wood Res. Soc. 6:122-128.nShibamoto, T., Y. Inoue, and Y. Kenjo. 1961b. Studies on water-borne wood preservatives XVIII: Color change of wood treated with colorants caused by weathering. J. Jpn. Wood Res. Soc. 6:147-151.nSlaughter, D. C., and R. C. Harrell. 1987. Color vision in robotic fruit harvesting. Trans. ASAE 30(4):1144-1148.nSmith, A. R. 1978. Color gamut transform pairs. Comput. Graphics 12(3):12-19.nSoest, J. F. 1987. Applications of optical measurements of slope of grain. Pages XII-1 to XII-10 in Proceedings, 2nd International Conference on Scanning Technology in Sawmilling. Miller Freeman, San Francisco, CA.nSproson, W. N. 1983. Colour science in television and display systems. Adam Hilger Ltd., Bristol, England.nSullivan, J. D. 1967a. Color characterization of wood: Spectrophotometry and wood color. Forest Prod. J. 17(7):43-48.nSullivan, J. D. 1967b. Color characterization of wood: Color parameters of individual species. Forest Prod. J. 17(8):25-29.nWandell, B. A. 1986. Color rendering of color camera data. COLOR Res. Appl. 11 (Suppl.):S30-S33.nWebb, D. A., and J. D. Sullivan. 1964. Surface effect of light and water on wood. Forest Prod. J. 14(11):531-534.nWyszecki, G., and W. S. Stiles. 1982. Color science: Concepts and methods, quantitative data and formulae, 2nd ed. John Wiley & Sons, New York.nYachida, M., and S. Tsuji. 1971. Application of color information to visual perception. Pattern Recognition 3:307-323.nZuech, N., and I. Miller. 1987. Machine vision. The Fairmont Press, Lilburn, GA.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.
