Evaluation of Binarization Algorithms for Camera-Based Devices

  • M. Nava-Ortiz
  • W. Gómez-Flores
  • A. Díaz-Pérez
  • G. Toscano-Pulido
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6718)

Abstract

Segmentation is an important step within optical character recognition systems, since the recognition rates depends strongly on the accuracy of binarization techniques. Hence, it is necessary to evaluate different segmentation methods for selecting the most adequate for a specific application. However, when gold patterns are not available for comparing the binarized outputs, the recognition rates of the entire system could be used for assessing the performance. In this article we present the evaluation of five local adaptive binarization methods for digit recognition in water meters by measuring misclassification rates. These methods were studied due to of their simplicity to be implemented in based-camera devices, such as cell phones, with limited hardware capabilities. The obtained results pointed out that Bernsens method achieved the best recognition rates when the normalized central moments are employed as features.

Keywords

local adaptive binarization optical character recognition camera-based devices feature selection 

References

  1. 1.
    Anagnostopoulos, C.N.E., Anagnostopoulos, I.E., Loumos, V., Kayafas, E.: A License Plate-Recognition Algorithm for Intelligent Transportation System Applications. IEEE Transactions on Intelligent Transportation Systems, 377–392 (2006)Google Scholar
  2. 2.
    Ji-yin, Z., Rui-rui, Z., Min, L., Yin, L.: License Plate Recognition Based on Genetic Algorithm. In: International Conference on Computer Science and Software Engineering, pp. 965–968 (2008)Google Scholar
  3. 3.
    Coughlan, J.H.S.: Reading lcd led displays with a camera cell phone. In: Conference on Computer Vision and Pattern Recognition Workshop (CVPRW 2006), pp. 119–119. IEEE Computer Society, Washington, DC, USA (2006)Google Scholar
  4. 4.
    Tian, L., Kamata, S.: An iterative image enhancement algorithm and a new evaluation framework. In: IEEE International Symposium on Industrial Electronics (ISIE 2008), pp. 992–997 (2008)Google Scholar
  5. 5.
    Thulke, M., Margner, V., Dengel, A.: Quality evaluation of document segmentation results. In: Proceedings of the Fifth International Conference on Document Analysis and Recognition, ICDAR 1999 (1999)Google Scholar
  6. 6.
    Trier, O.D., Jain, A.K.: Goal-directed evaluation of binarization methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1191–1201 (1995)Google Scholar
  7. 7.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Prentice-Hall, NewJersey (2002)Google Scholar
  8. 8.
    J. Bernsen.: Dynamic thresholding of gray-level images. In: Proc. Eighth Int. Conf. Pattern Recognition, pp. 1251–1255 (1986)Google Scholar
  9. 9.
    Niblack, W.: An Introduction to Digital Image Processing, pp. 115–116. Prentice Hall, Englewood Cliffs (1986)Google Scholar
  10. 10.
    Sauvola, J., Pietikinen, M.: Adaptive document image binarization. Pattern Recognition 33(2), 225–236 (2000)CrossRefGoogle Scholar
  11. 11.
    Wellner, P. D.: Adaptive Thresholding for the DigitalDesk. Technical Report EPC-1993-110, Rank Xerox Ltd. (1993)Google Scholar
  12. 12.
    White, J.M., Rohrer, G.D.: Image thresholding for optical character recognition and other applications requiring character image extraction. IBMJ. Research and Development 27(4), 400–411 (1983)CrossRefGoogle Scholar
  13. 13.
    Rais, N.B., Hanif, M.S., Taj, I.A.: Adaptive thresholding technique for document image analysis. In: Proc: 8th International Multitopic Conference, pp. 61–66 (2004)Google Scholar
  14. 14.
    Huang, Z., Leng, J.: Analysis of hu’s moment invariants on image scaling and rotation. In: 2nd International Conference on Computer Engineering and Technology (ICCET 2010), vol. 7, pp. 476–480. IEEE Computer Society, Los Alamitos (2010)Google Scholar
  15. 15.
    Liu, H., Motoda, H.: Computational Methods of Feature Selection. Taylor & Francis, Boca Raton (2008)MATHGoogle Scholar
  16. 16.
    Gómez, W., Leija, L., Díaz-Pérez, A.: Mutual Information and Intrinsic Dimensionality for Feature Selection. In: 7th International Conference on Electrical Engineering,Computing Sciences and Automatic Control (CCE 2010), Tuxtla Gutiérrez, Chiapas, September 8–10, pp. 339–344 (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • M. Nava-Ortiz
    • 1
  • W. Gómez-Flores
    • 1
  • A. Díaz-Pérez
    • 1
  • G. Toscano-Pulido
    • 1
  1. 1.Information Technology LaboratoryCINVESTAV-IPNMexico

Personalised recommendations