Advertisement

Recognition of wood surface defects with near infrared spectroscopy and machine vision

  • Huiling Yu
  • Yuliang Liang
  • Hao Liang
  • Yizhuo ZhangEmail author
Original Paper

Abstract

To improve the accuracy in recognizing defects on wood surfaces, a method fusing near infrared spectroscopy (NIR) and machine vision was examined. Larix gmelinii was selected as the raw material, and the experiments focused on the ability of the model to sort defects into four types: live knots, dead knots, pinholes, and cracks. Sample images were taken using an industrial camera, and a morphological algorithm was applied to locate the position of the defects. A portable near infrared spectrometer (900–1800 nm) collected the spectra of these positions. In addition, principal component analysis was utilized on these variables from spectral information and principal component vectors were extracted as the inputs of the model. The results show that a back propagation neural network model exhibited better discrimination accuracy of 92.7% for the training set and 92.0% for the test set. The research reveals that the NIR fusing machine vision is a feasible tool for detecting defects on board surfaces.

Keywords

Wood board surface defects Near infrared spectroscopy Machine vision Accuracy of recognition 

References

  1. Cao J, Liang H, Lin X, Zhang Y (2017) Potential of near-infrared spectroscopy to detect defects on the surface of solid wood boards. BioResources 12(1):19–28.  https://doi.org/10.15376/biores.12.1.19-28 Google Scholar
  2. Chacon MI, Alonso GR (2006) Wood defects classification using a SOM/FFP approach with minimum dimension feature vector. In: International symposium on advances in neural networks-isnn, vol 3973, pp 1105–1110Google Scholar
  3. Chang ZY, Cao J, Zhang YZ (2018) A novel image segmentation approach for wood plate surface defect classification through convex optimization. J For Res 29(6):1789–1795Google Scholar
  4. Gu YH, Andersson H, Vicen R (2010) Wood defect classification based on image analysis and support vector machines. Wood Sci Technol 44(4):693–704.  https://doi.org/10.1007/s00226-009-0287-9 Google Scholar
  5. Inagaki T, Schwanninger M, Kato R, Kurata Y, Thanapase W, Puthson P, Tsuchikawa S (2012) Eucalyptus camaldulensis density and fiber length estimated by near infrared spectroscopy. Wood Sci Technol 46(1):143–155.  https://doi.org/10.1007/s00226-010-0379-6 Google Scholar
  6. Jones PD, Schimleck LR, Peter GF, Daniels RF, Clark A III (2006) Nondestructive estimation of wood chemical composition of sections of radial wood strips by diffuse reflectance near infrared spectroscopy. Wood Sci Technol 40(8):709–720.  https://doi.org/10.1007/s00226-006-0085-6 Google Scholar
  7. Ledoux A, Richard N (2016) Color and multiscale texture features from vectorial mathematical morphology. SIViP 10(3):431–438.  https://doi.org/10.1007/s11760-015-0759-3 Google Scholar
  8. Li C, Su YW, Zhang YZ, Yang HM (2017a) Root imaging from ground penetrating radar data by CPSO-OMP compressed sensing. J For Res 28(1):155–162.  https://doi.org/10.1007/s11676-016-0284-4 Google Scholar
  9. Li C, Zhang Y, Tu W, Cao J, Liang H, Yu HL (2017b) Soft measurement of wood defects based on LDA feature fusion and compressed sensor images. J For Res 28(6):1285–1292.  https://doi.org/10.1007/s11676-017-0395-6 Google Scholar
  10. Liang H, Cao J, Tu WJ, Lin X, Zhang YZ (2016) Nondestructive determination of the compressive strength of wood using near-infrared spectroscopy. BioResources 11(3):7205–7213.  https://doi.org/10.15376/biores.11.3.7205-7213 Google Scholar
  11. Moore B (1981) Principal component analysis in linear systems: controllability, observability, and model reduction. IEEE Trans Autom Control 26(1):17–32.  https://doi.org/10.1109/TAC.1981.1102568 Google Scholar
  12. Mosorov V, Tomczak L (2014) Image texture defect detection method using fuzzy C-means clustering for visual inspection systems. Arab J Sci Eng 39(4):3013–3022.  https://doi.org/10.1007/s13369-013-0920-7 Google Scholar
  13. Perona P, Malik J (1990) Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 12(7):629–639.  https://doi.org/10.1109/34.56205 Google Scholar
  14. Pham DT, Alcock RJ (1998) Automated grading and defect detection: a review. For Prod J 48(4):34–42Google Scholar
  15. Satoru T, Hikaru K (2015) A review of recent application of near infrared spectroscopy to wood science and technology. J Wood Sci 61(3):213–220.  https://doi.org/10.1007/s10086-015-1467-x Google Scholar
  16. Schubert M, Mourad S, Schwarze FWMR (2011) Automated image processing for quantification of blue-stain discolouration of Norway spruce wood. Wood Sci Technol 45(2):331–337.  https://doi.org/10.1007/s00226-010-0328-4 Google Scholar
  17. Sundaram J, Mani S, Kandala CVK (2015) Application of NIR reflectance spectroscopy on rapid determination of moisture content of wood pellets. Am J Anal Chem 06(12):923–932.  https://doi.org/10.4236/ajac.2015.612088 Google Scholar
  18. Yang Z, Zhang MM, Li K, Chen L (2016) Rapid detection of knot defects on wood surface by near infrared spectroscopy coupled with partial least squares discriminant analysis. BioResources 11(1):2557–2567.  https://doi.org/10.15376/biores.11.1.2557-2567 Google Scholar

Copyright information

© Northeast Forestry University 2019

Authors and Affiliations

  • Huiling Yu
    • 1
  • Yuliang Liang
    • 1
  • Hao Liang
    • 1
  • Yizhuo Zhang
    • 1
    Email author
  1. 1.Northeast Forestry UniversityHarbinPeople’s Republic of China

Personalised recommendations