Skip to main content
SpringerLink
Log in

Comparison of different approaches for automatic bark detection on log images

  • Original Paper
  • Published:
Wood Science and Technology Aims and scope Submit manuscript

Abstract

The sawmilling industry stores and measures logs with bark in order to maximize efficiency, quality conservation and preservation. However since billing is based on the diameter under bark, it is necessary to differentiate between bark areas and wood areas automatically or via manual assignment. This paper compares different methodologies to automatically differentiate between these areas based on colour images of the log surface of two species, spruce and pine. Additionally, the performance of the different methodologies is evaluated using the proportion of correctly detected bark areas, correctly detected wood areas and the total amount of detected bark and wood areas. In the end, an algorithm taking into account colour and texture information was found to perform well on both species. Based on a larger dataset, this methodology has the potential to detect the diameter under bark based on measurements of logs with bark.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  • Altherr E, Unfried P, Hradetzky J, Hradetzky V (1974) Statistische Rindenbeziehungen als Hilfsmittel zur Ausformung und Aufmessung unentrindeten Stammholzes. Teil I: Lärche, Schwarzkiefer, Eiche, Bergahorn, Linde. Mitteilungen der Forstlichen Versuchs- und Forschungsanstalt Baden-Württemberg 61

  • Chiorescu S, Grundberg S (2001) The influence of missing bark on measurements performed with a 3D log scanner. For Prod J 51:78–86

    Google Scholar 

  • Clausi DA (2002) An analysis of co-occurrence texture statistics as a function of grey level quantization. Can J Remote Sens 28:45–62

    Article  Google Scholar 

  • Flodin J, Oja J, Grönlund A (2008) Fingerprint traceability of logs using the outer shape and the tracheid effect. For Prod J 58:21–27

    Google Scholar 

  • Goldberg DE (1989) Genetic algorithms in search, optimization, and machine learning. Addison-Wesley, Reading, MA (Repr. with corr)

    Google Scholar 

  • Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3:610–621

    Article  Google Scholar 

  • Huang Z, Huang D, Quan Z (2006) Bark Classification using RBPNN Based on Gabor Filter in Different Color Space: IEEE International Conference on Information Acquisition. Aug 2006, Weihai, China, pp 946–950

  • Jähne B (1997) Digital image processing. Concepts, algorithms, and scientific applications. 4th edn, complete revision. Springer, Berlin

  • Lakmann R (1998) BarkTex benchmark database of color textured images. ftp://ftphost.uni-koblenz.de/outgoing/vision/Lakmann/BarkTex. Accessed 21 Dec 2010

  • Nilsson D, Edlund U (2005) Pine and spruce roundwood species classification using multivariate image analysis on bark. Holzforschung 59:689–695

    Article  CAS  Google Scholar 

  • Palm C (2004) Color texture classification by integrative co-occurrence matrices. Pattern Recognit. 37:965–976

    Article  Google Scholar 

  • Porebski A, Vandenbroucke N, Macaire L (2006) Neighborhood and Haralick feature extraction for color texture analysis. In: Luo R (ed) Proceedings of the CGIV 2008/MCS’08. 4th European conference on colour in graphics, imaging, and vision, 10th international symposium on multispectral colour science. IS&T, Springfield, VA, pp 316–321

  • Soh L-, Tsatsoulis C (1999) Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Trans Geosci Remote Sens 37:780–795

    Article  Google Scholar 

  • Uppuluri A (2008) GLCM texture features. Matlab Central, The Mathworks. http://www.mathworks.com/matlabcentral/fileexchange/22187-glcm-texture-features. Accessed 22 March 2011

Download references

Acknowledgments

This work was supported by the Austrian Research Promotion Agency (FFG) and Wirtschaftsagentur Wien (ZIT) within the COMET K-project “HFA-TiMBER A.1.1”, (Project nr. 820501). We also thank our project partners Donausäge Rumplmayr GmbH, MiCROTEC s.r.l. and the University of Applied Sciences Salzburg, Department for Research and Development.

Author information

Authors and Affiliations

  1. Holzforschung Austria, Franz-Grill-Straße 7, 1030, Vienna, Austria

    Julia K. Denzler, Andreas Weidenhiller & Michael Golser

Authors
  1. Julia K. Denzler
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Andreas Weidenhiller
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Michael Golser
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Andreas Weidenhiller.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Denzler, J.K., Weidenhiller, A. & Golser, M. Comparison of different approaches for automatic bark detection on log images. Wood Sci Technol 47, 749–761 (2013). https://doi.org/10.1007/s00226-013-0536-9

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00226-013-0536-9

Keywords

Search

Navigation