A Generic Approach to the Texture Detection Problem in Digital Images
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.
KeywordsSupport Vector Machine Detection Problem Average Calculation Time Planar Marker Haralick Feature
Unable to display preview. Download preview PDF.
- 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
- 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.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
- 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.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.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.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.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.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.Schalkoff, R.J.: Digital Image Processing and Computer Vision. Wiley, Chichester (1989)Google Scholar
- 14.Theodoridis, S., Koutroumbas, K.: Pattern Recognition, 4th edn. Academic Press, London (2009)Google Scholar