A Generic Approach to the Texture Detection Problem in Digital Images

  • Christian Feinen
  • Marcin Grzegorzek
  • Detlev Droege
  • Dietrich Paulus
Conference paper
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 95)


In this paper, we describe our solution to the marker detection problem in digital images. In order to keep our investigations as general as possible, our approach has not been developed in an application-drivenway. However,we have evaluated the system for the bar code detection problem. To represent the markers, our system uses general feature extraction methods like Hu Moments and the Fourier- Mellin transform which are both invariant to rotation, scaling and translation. For marker classification, Bayes Classifier and Support Vector Machine have been applied. A comprehensive set of experiments performed for our algorithm proved its high robustness for a challenging set of images.


Support Vector Machine Detection Problem Average Calculation Time Planar Marker Haralick Feature 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Duda, R.O., Hart, P.E.: Use of the hough transformation to detect lines and curves in pictures. Commun. ACM 15, 11–15 (1972)CrossRefGoogle Scholar
  2. 2.
    Fiala, M.: Artag, a fiducial marker system using digital techniques. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 2, pp. 590–596 (2005)Google Scholar
  3. 3.
    Haralick, R.M., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Transactions on Systems, Man and Cybernetics 3(6), 610–621 (1973)CrossRefGoogle Scholar
  4. 4.
    Hirzer, M.: Marker detection for augmented reality applications. Tech. rep., Institution for Computer Graphics and Vision, Graz University of Technology, Austria (2008)Google Scholar
  5. 5.
    Hu, H., Xu, W., Huang, Q.: A 2d barcode extraction method based on texture direction analysis. In: Fifth International Conference on Image and Graphics, ICIG 2009, pp. 759–762 (2009)Google Scholar
  6. 6.
    Hu, M.K.: Visual pattern recognition by moment invariants. IRE Transactions on Information Theory 8(2), 179–187 (1962)CrossRefGoogle Scholar
  7. 7.
    Jin, A.T.B., Ling, D.N.C.: Integrated wavelet and fourier-mellin invariant feature in fingerprint verification system. In: Proceedings of the ACM SIGMM Workshop on Biometrics Methods and Applications, WBMA 2003, pp. 82–88. ACM, New York (2003)Google Scholar
  8. 8.
    Liang, Y.H., Wang, Z.Y.: A skew detection method for 2d bar code images based on the least square method. In: 2006 International Conference on Machine Learning and Cybernetics, pp. 3974–3977 (2006)Google Scholar
  9. 9.
    Longacre Jr., A., Hussey, R.: Two dimensional data encoding structure and symbology for use with optical readers (1997), U.S. Patent No. 5,591,956 (“Aztec-Code”) Google Scholar
  10. 10.
    Nakthanom, S., Choomchuay, S.: A 2d barcode inspection using template matching. In: Proceedings of the 3rd International Conference on Data Storage Technology (DST-CON 2010) (2010)Google Scholar
  11. 11.
    Parvu, O., Balan, A.G.: A method for fast detection and decoding of specific 2d barcodes. In: Proceedings of the 17th Telecommunications forum TELFOR 2009, pp. 1137–1140 (2009)Google Scholar
  12. 12.
    Rau, J.Y., Chen, L.C.: Fast straight lines detection using hough transform with principal axis analysis. Transform 8(1), 1–17 (2003)Google Scholar
  13. 13.
    Schalkoff, R.J.: Digital Image Processing and Computer Vision. Wiley, Chichester (1989)Google Scholar
  14. 14.
    Theodoridis, S., Koutroumbas, K.: Pattern Recognition, 4th edn. Academic Press, London (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Christian Feinen
    • 1
  • Marcin Grzegorzek
    • 1
  • Detlev Droege
    • 2
  • Dietrich Paulus
    • 2
  1. 1.Research Group for Pattern RecognitionUniversity of SiegenGermany
  2. 2.Research Group for Active VisionUniversity of Koblenz-LandauGermany

Personalised recommendations