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

详细信息    查看全文

• 作者：Peng Zhao ; Jun Cao
• 关键词：Wood species identification ; Feature selection ; Radian ; Genetic algorithm ; Spectral analysis
• 刊名：Journal of Forestry Research
• 出版年：2016
• 出版时间：February 2016
• 年：2016
• 卷：27
• 期：1
• 页码：219-224
• 全文大小：653 KB
• 参考文献：Chen GS, Zhao P (2012) Dynamic wood slice recognition using image blur information. Sens Actuators A 176:27–33CrossRef
  Lavine BK, Davidson CE, Moores AJ, Griffiths PR (2001) Raman spectroscopy and genetic algorithms for the classification of wood types. Appl Spectrosc 55(8):960–966CrossRef
  Moore AK, Owen NL (2001) Infrared spectroscopic studies of solid wood. Appl Spectrosc Rev 36(1):65–86CrossRef
  Nakamura M, Masuda M, Shinohara K (1999) Multiresolutional image analysis of wood and other materials. J Wood Sci 45(1):10–18CrossRef
  Orton CR, Parkinson DY, Evans PD, Owen NL (2004) Fourier transform infrared studies of heterogeneity, photodegradation, and lignin/hemicellulose ratios within hardwoods and softwoods. Appl Spectrosc 58(11):1265–1271PubMed CrossRef
  Packianather MS, Drake PR (2000) Neural networks for classifying images of wood veneer. Int J Adv Manuf Technol 16(6):424–433CrossRef
  Phelps JE, Mcginnes EA (1983) Growth-quality evaluation of black walnut wood, Part 2—color analysis of veneer produced on different sites. Wood Fiber Sci 15(2):177–185
  Piuri V, Scotti F (2010) Design of an automatic wood types classification system by using fluorescence spectra. IEEE Trans SMC C 40(3):358–366
  Qiang W, Ying HC, Brigitte L, Shu YZ (2009) Identification of selected internal wood characteristics in computed tomography images of black spruce: a comparison study. J Wood Sci 55(3):175–180CrossRef
  Tsuchikawa S, Hirashima Y, Sasaki Y, Ando K (2005) Near-infrared spectroscopic study of the physical and mechanical properties of wood with meso- and micro-scale anatomical observation. Appl Spectrosc 59(1):86–93PubMed CrossRef
  
• 作者单位：Peng Zhao (1)
  Jun Cao (2)
  
  1. Information and Computer Engineering College, Northeast Forestry University, 150040, Harbin, China
  2. College of Mechanical and Electronic Engineering, Northeast Forestry University, 150040, Harbin, China
  
• 刊物主题：Forestry;
• 出版者：Springer Berlin Heidelberg
• ISSN：1993-0607

文摘

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.