Skip to main content

Official Journal of the Japan Wood Research Society

Journal of Wood Science Cover Image

Identification of selected internal wood characteristics in computed tomography images of black spruce: a comparison study


The feasibility of identifying internal wood characteristics in computed tomography (CT) images of black spruce was investigated using two promising classifiers: the maximum likelihood classifier (MLC) and the back propagation (BP) artificial neural network (ANN) classifier. Nine image features including one spectral feature (gray level values), a distance feature, and seven textural features were employed to develop the classifiers. The selected internal wood characteristics to be identified included heartwood, sapwood, bark, and knots. Twenty cross-sectional CT images of a black spruce log were randomly selected to develop the two classifiers. The results suggest that both classifiers produced high classification accuracy. Compared with the MLC classifier (80.9% overall accuracy), the BP ANN classifier had better classification performance (97.6% overall accuracy). Moreover, statistical analysis reveals that the heartwood of the black spruce log used in this study is the easiest to identify by either classifier compared with the other three log features. The results also suggest that the separability of one wood characteristic from the other wood characteristics in black spruce CT images is mainly related to moisture content.


  1. 1.

    Steele PH, Taylor FW (1989) Hardwood sawing methods to maximize value and volume: preliminary results. Proceedings of the 7th Annual Hardwood Symposium, Milwaukee, Wisconsin, USA, pp 149–166

  2. 2.

    Thomas E, Bush K (1998) Log scanning: an alternative approach. Proceedings of the 8th International Conference on Scanning Technology and Process Optimization for the Wood Products Industry, Vancouver, British Columbia, Canada, pp 141–151

  3. 3.

    Faust TD, Tang MJ (1996) A software system for detection and display of internal defects in logs using axial CT images. International Workshop on Applied Computer Vision, Sarasota, Florida, USA, pp 258–263

  4. 4.

    Schmoldt DL, Scheinman E, Rinnhofer A, Occena LG (2000) Internal log scanning: research to reality. Proceedings of 28th Annual Hardwood Symposium, Memphis, TN, USA, pp 103–114

  5. 5.

    Harless TEG, Wagner FH, Taylor FW, Yadama V, McMillin CW (1991) Methodology for locating defects within hardwood logs and determining their impact on lumber-value yield. Forest Prod J 41:25–30

    Google Scholar 

  6. 6.

    Funt BV, Bryant EC (1987) Detection of internal log defects by automatic interpretation of computer tomography images. Forest Prod J 37:56–62

    Google Scholar 

  7. 7.

    Araujo CG, MacKay AL, Hailey JRT, Whittall KP (1992) Proton magnetic resonance techniques for characterization of water in wood: application to white spruce. Wood Sci Technol 26:101–113

    CAS  Article  Google Scholar 

  8. 8.

    Leininger TD, Schmoldt DL, Tainter FH (2001) Using ultrasound to detect defects in trees: current knowledge and future needs. Proceedings of the 1st International Precision Forestry Cooperative Symposium, Seattle, Washington, USA, pp 99–107

  9. 9.

    Gjerdrum P, Hoibo O (2004) Heartwood detection in Scots pine by means of heat-sensitive infrared images. Holz Roh Werkst 62:131–136

    Article  Google Scholar 

  10. 10.

    Kaestner AP, Bååth LB (2005) Microwave polarimetry tomography of wood. IEEE Sens J 5:209–215

    Article  Google Scholar 

  11. 11.

    Bucur V (2003) Nondestructive characterization and imaging of wood. Springer Series in Wood Science, Springer, Berlin Heidelberg New York, pp 9, 20, 21

    Google Scholar 

  12. 12.

    Lindgren LO (1985) On the relationship between density/moisture content in wood and X-ray attenuation in computer tomography. Proceedings of the Fifth Symposium Nondestructive Testing of Wood, Washington State University, Pullman, USA, pp 193-203

  13. 13.

    Oja J, Temnerud E (1999) The appearance of resin pockets in CTimages of Norway spruce (Picea abies (L.) karst). Holz Roh Werkst 57:400–406

    Article  Google Scholar 

  14. 14.

    Wiberg P, Moren TJ (1999) Moisture flux determination in wood during drying above fiber saturation point using CT-scanning and digital image processing. Holz Roh Werkst 57:137–144

    CAS  Article  Google Scholar 

  15. 15.

    Zhu DP (1996) A prototype vision system for analyzing CT imagery of hardwood logs. IEEE Trans Syst Man Cybern 26:522–532

    CAS  Article  Google Scholar 

  16. 16.

    Schmoldt DL, He J, Abbott AL (2000) Automated labeling of log features in CT imagery of multiple hardwood species. Wood Fiber Sci 32:287–300

    CAS  Google Scholar 

  17. 17.

    Nordmark U (2002) Knot identification from CT images of young Pinus sylvestris sawlogs using artificial neural networks. Scand J Forest Res 17:72–78

    Article  Google Scholar 

  18. 18.

    Rojas G, Condal A, Beauregard R, Verret D, Hernandez RE (2006) Identification of internal defect of sugar maple logs from CT images using supervised classification methods. Holz Roh Werkst 64:295–303

    Article  Google Scholar 

  19. 19.

    Riedmiller M, Braun H (1993) A direct adaptive method for faster back-propagation learning: the RPROP algorithm. Proceedings of IEEE International Conference on Neural Networks, San Francisco, California, USA, pp 828–845

  20. 20.

    Hou ZQ, Zhang SY, Hu LJ (2005) Determining wood density and its 3-D distribution in a log using computed tomography scanning technique. Proceedings of 14th International Symposium on Nondestructive Testing of Wood, Shaker, Germany, pp 427–433

  21. 21.

    Bond BH, Kline DE, Araman PA (1998) Characterization of defects in lumber using color, shape and density information. Proceedings of 1998 International Conference on Multisource-Multisensor Information Fusion, Las Vegas, NV, USA, pp 581–587

  22. 22.

    Wei Q, Leblon B, Chui YH, Zhang SY (2008) Identification of selected log characteristics from computed tomography images of sugar maple logs using maximum likelihood classifier and textural analysis. Holzforschung 62:441–447

    CAS  Article  Google Scholar 

  23. 23.

    Mcleish E (2006) Decision rules. Faculty of Computer Science, University of McGill, Montreal, Quebec. Cited June 2007

  24. 24.

    Mas JF, Flores JJ (2008) The application of artificial neural networks to the analysis of remotely sensed data. Int J Remote Sens 29:617–663

    Article  Google Scholar 

  25. 25.

    Wei Q, Chui YH, Leblon B, Zhang SY (2008) Identification of log characteristics in computed tomography images using backpropagation neural networks with the resilient back-propagation training algorithm and textural analysis: preliminary results. Wood Fiber Sci 40:620–633

    CAS  Google Scholar 

  26. 26.

    Congalton R (1991) A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens Environ 37:35–46

    Article  Google Scholar 

  27. 27.

    Li P, He J, Abbott L, Schmoldt DL (1996) Labeling defects in CT images of hardwood logs with species-dependent and speciesindependent classifiers. Proceedings of IAPR TC-8 Workshop on Machine Perception Applications, Technical University Graz, Austria, pp 113–126

    Google Scholar 

  28. 28.

    Ghosh MN, Sharma D (1963) Power of Tukey’s test for nonadditivity. J Roy Stat Soc 25B:213–219

    Google Scholar 

  29. 29.

    Rojas G (2005) Detection of internal defaults in sugar maple logs using X-ray. PhD Thesis. Department of Wood and the Forest, University Laval, Quebec, Canada, pp 40–46

    Google Scholar 

  30. 30.

    Panshin AJ, Zeeuw CD (1971) Textbook of wood technology, vol 1, 3rd edn. McGraw-Hill, New York, pp 252–253

    Google Scholar 

  31. 31.

    Zhang SY, Morgenstern EK (1995) Genetic variation and inheritance of wood density in black spruce (Picea mariana) and its relationship with growth: implication for tree breeding. Wood Sci Technol 30:63–75

    Article  Google Scholar 

  32. 32.

    Forest Products Laboratory (1999) Wood handbook: wood as an engineering material. General Technical Report FPL-GTR-113. US Department of Agriculture, Madison, WI, USA, pp 3–6

    Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Qiang Wei.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Wei, Q., Chui, Y.H., Leblon, B. et al. Identification of selected internal wood characteristics in computed tomography images of black spruce: a comparison study. J Wood Sci 55, 175–180 (2009).

Download citation

Key words

  • Artificial neural network (ANN)
  • Black spruce
  • Computed tomography (CT) images
  • Internal wood features
  • Maximum likelihood classifier (MLC)