Skip to main content

A Robust Modular Wavelet Network Based Symbol Classifier

  • Conference paper
Image Analysis and Recognition (ICIAR 2009)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 5627))

Included in the following conference series:

  • 2163 Accesses

Abstract

This paper presents a robust automatic shape classifier using modular wavelet networks (MWNs). A shape descriptor is constructed based on a combination of global geometric features (modified Zernike moments and circularity features) and local intensity features (ordered histogram of image gradient orientations). The proposed method utilizes a supervised modular wavelet network to perform shape classification based on the extracted shape descriptors. Affine invariance is achieved using a novel eigen-based normalization approach. Furthermore, appropriate shape features are selected based on the inter- and intra-class separation indices. Therefore, the proposed classifier is robust to scale, translation, rotation and noise. Modularity is introduced to the wavelet network to decompose the complex classifier into an ensemble of simple classifiers. Wavelet network parameters are learned using an extended Kalman filter (EKF). The classification performance of proposed approaches is tested on a variety of standard symbol data sets (i.e., mechanical tools, trademark, and Oriya numerals) and the average classification accuracy is found to be 98.1% which is higher compared to other shape classifier techniques.

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Jain, A., Vailaya, A.: Shape-based retrieval: A case-study with trademark image databases. Pattern Recognition 31(9), 1369–1390 (1998)

    Article  Google Scholar 

  2. Badawy, O., Kamel, M.: Shape-based image retrieval applied to trademark images, pp. 373–392 (2004)

    Google Scholar 

  3. Hou, T., Pern, M.: A shape classifier by using image projection and a neural network. IJPRAI 14(2), 225–242 (2000)

    Google Scholar 

  4. Zhenjiang, M.: Zernike moment-based image shape analysis and its application. Pattern Recognition Letter 21(2), 169–177 (2000)

    Article  Google Scholar 

  5. Osowski, S., Nghia, D.: Fourier and wavelet descriptors for shape recognition using neural networksa comparative study. Pattern Recognition 35(9), 1949–1957 (2002)

    Article  MATH  Google Scholar 

  6. Choi, M., Kim, W.: A novel two stage template matching method for rotation and illumination invariance. Pattern Recognition 35(1), 119–129 (2002)

    Article  MATH  Google Scholar 

  7. Tsai, D.: An improved generalized Hough transform for the recognition of overlapping objects. IVC 15(12), 877–888 (1997)

    Article  Google Scholar 

  8. Khotanzad, A., Hong, Y.H.: Invariant image recognition by Zernike moments. IEEE Transaction on Pattern Analysis and Machine Intelligence 12(5), 489–497 (1990)

    Article  Google Scholar 

  9. Wallin, A., Kubler, O.: Complete sets of complex Zernike moment invariants and the role of the pseudoinvariants. IEEE Transaction on Pattern Analysis and Machine Intelligence 17(11), 1106–1110 (1995)

    Article  Google Scholar 

  10. Kim, W., Kim, Y.: A region-based shape descriptor using Zernike moments 16(1-2), 95–102 (September 2000)

    Google Scholar 

  11. Daqi, G., Chunxia, L., Yunfan, Y.: Task decomposition and modular single-hidden-layer perceptron classifiers for multi-class learning problems. Pattern Recognition 40(8), 2226–2236 (2007)

    Article  MATH  Google Scholar 

  12. Postalcioglu, S., Yasar, B.: Wavelet networks for nonlinear system modeling. Neural Computing and Applications 16(4-5) (May 2000)

    Google Scholar 

  13. Pradhan, A., Routray, A., Behera, A.: Power quality disturbance classification employing modular wavelet network. In: Power Engineering Society General Meeting, Montreal, Que, p. 5. IEEE, Los Alamitos (2006)

    Google Scholar 

  14. Liu, F., Luo, L.: Immune clonal selection wavelet network based intrusion detection. In: ICANN, vol. 1, pp. 331–336 (2005)

    Google Scholar 

  15. Postalcioglu, S., Yasar, B.: Gradient-based polyhedral segmentation for range images. Pattern Recognition Letter 24(12), 2069–2077 (2003)

    Article  Google Scholar 

  16. Oh, S., Lee, J., Ching, Y.S.: Analysis of class separation and combination of class-dependent features for handwriting recognition. IEEE Transaction on Pattern Analysis and Machine Intelligence 21(10) (1999)

    Google Scholar 

  17. Otsu, N.: A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man and Cybernetics 9(1), 62–66 (1979)

    Article  MathSciNet  Google Scholar 

  18. Roy, K., Pal, T., Pal, U., Kimura, F.: Oriya handwritten numeral recognition syste. In: ICDAR 2005: Proceedings of the Eighth International Conference on Document Analysis and Recognition, Washington, DC, USA, pp. 770–774. IEEE Computer Society, Los Alamitos (2005)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2009 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Mishra, A.K., Fieguth, P.W., Clausi, D.A. (2009). A Robust Modular Wavelet Network Based Symbol Classifier. In: Kamel, M., Campilho, A. (eds) Image Analysis and Recognition. ICIAR 2009. Lecture Notes in Computer Science, vol 5627. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02611-9_54

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-02611-9_54

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-02610-2

  • Online ISBN: 978-3-642-02611-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics