Skip to main content
Log in

Invariance analysis of modified C2 features: case study—handwritten digit recognition

  • Short Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

Humans are very efficient in recognizing alphanumeric characters, even in the presence of significant image distortions. Recent advances in visual neuroscience have led to a solid model of object and shape recognition in the visual ventral stream which competes with the state-of-the-art computer vision systems on some standard recognition tasks. A modification of this model is also proposed by adding more biologically inspired properties such as sparsification of features, lateral inhibition and feature localization to enhance its performance. In this study, we show that using features proposed by the modified model results in higher handwritten digit recognition rates compared with the original model over English and Farsi handwritten digit datasets. Our analyses also demonstrate higher invariance of the modified model to various image distortions.

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

Access this article

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

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Logothetis N.K., Pauls J., Poggio T.: Shape representation in the inferior temporal cortex of monkeys. Curr. Biol. 5, 552–563 (1995)

    Article  Google Scholar 

  2. Riesenhuber M., Poggio T.: Hierarchical models of object recognition in cortex. Nat. Neurosci. 2(11), 1019–1025 (1999)

    Article  Google Scholar 

  3. Serre, T., Kouh, M., Cadieu, C., Knoblich, U., Kreiman, G., Poggio, T.: A theory of object recognition: computations and circuits in the feedforward path of the ventral stream in primate visual cortex. Technical Report CBCL Paper #259/AI Memo #2005-036, Massachusetts Institute of Technology, Cambridge, MA, October 2005

  4. Serre T., Oliva A., Poggio T.A.: A feedforward architecture accounts for rapid categorization. Proc. Natl. Acad. Sci. USA 104(15), 6424–6642 (2007)

    Article  Google Scholar 

  5. Serre T., Wolf L., Bileschi S., Riesenhuber M., Poggio T.: Object recognition with cortex like mechanisms. IEEE Trans. PAMI 29(3), 411–426 (2007)

    Google Scholar 

  6. Govindaraju, V., Shekhawat, A., Srihari, S.N.: Interpretation of handwritten addresses in US mail stream. In: The Third International Workshop on Frontiers in Handwriting Recognition, Buffalo, New York, pp. 197–206 (1994)

  7. Belaid, Y., Belaid, A., Turolla, E.: Item searching in forms: application to french tax form. In: International Conference on Document Analysis and Recognition, Montreal, Canada, pp. 744–747 (1995)

  8. Gader P.D., Forester B., Ganzberger M., Gillies A., Mitchell B., Whalen M., Yocum T.: Recognition of handwritten digits using template and model matching. Pattern Recognit. 24(5), 421–431 (1991)

    Article  Google Scholar 

  9. Freitas C.O.A., Oliveira L.E.S., Bortolozzi F., Aires S.B.K.: Handwritten character recognition using non-symmetrical perceptual zoning. Int. J. Pattern Recognit. Artif. Intell. 21(1), 135–155 (2007)

    Article  Google Scholar 

  10. Wang, D., Xie, W.: Invariant image recognition by neural networks and modified moment invariants. In: Proceedings of SPIE’96 (1996)

  11. Kauppinen, H., et al.: An experimental comparison of autoregressive and Fourier-based descriptors in 2D shape classification. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 2 (1995)

  12. Di Zenzo S. et al.: Optical recognition of hand-printed characters of any size, position, and orientation. IBM J. Res. Dev. 36(3), 487–501 (1992)

    Article  Google Scholar 

  13. Belkasim S.O. et al.: Shape recognition using Zernike moment invariants. Asilomar Conf. Circuits 1, 161–171 (1989)

    Google Scholar 

  14. Shi M., Fujisawa Y., Wakabayashi T., Kimura F.: Handwritten numeral recognition using gradient and curvature of gray scale image. Pattern Recognit. 35, 2051–2059 (2002)

    Article  MATH  Google Scholar 

  15. Wang X., Ding X., Liu C.: Gabor filters-based feature extraction for character recognition. Pattern Recognit. 38(3), 369–379 (2005)

    Article  MATH  MathSciNet  Google Scholar 

  16. Liu C.L. et al.: Handwritten digit recognition: benchmarking of state-of-the-art techniques. Pattern Recognit. 36, 2271–2285 (2003)

    Article  MATH  Google Scholar 

  17. Teow L.N., Loe K.F.: Robust vision-based features and classification schemes for off-line handwritten digit recognition. Pattern Recognit. 35, 2355–2364 (2002)

    Article  MATH  Google Scholar 

  18. Cheung K., Yeung D., Chin R.T.: A Bayesian framework for deformable pattern recognition with application to handwritten character recognition. IEEE Trans. Pattern Anal. Mach. Intell. 29(12), 1382–1388 (1998)

    Article  Google Scholar 

  19. Tsang, I.J., Tsang, I.R., Dyck D.V.: Handwritten character recognition based on moment features derived from image partition. In: International Conference on Image Processing 2, pp. 939–942 (1998)

  20. Soltanzadeh H., Rahmati M.: Recognition of Persian handwritten digits using image profiles of multiple orientations. Pattern Recognit. Lett. 25(14), 1569–1576 (2004)

    Article  Google Scholar 

  21. Said, F.N., Yacoub, R.A., Suen, C.Y.: Recognition of English and Arabic numerals using a dynamic number of hidden neurons. In: Proceedings of the Fifth International Conference on Document Analysis and Recognition, pp. 237–240 (1999)

  22. Sadri, J., Suen, C.Y., Bui, T.D.: Application of support vector machines for recognition of handwritten Arabic/Persian digits. In: Proceedings of Second Iranian Conference on Machine Vision and Image Processing 1, pp. 300S–307S (2003)

  23. Borji A., Hamidi M., Mahmoudi F.: Robust handwritten character recognition with features inspired by visual ventral stream. Neural Process. Lett. 28(2), 97–111 (2008)

    Article  Google Scholar 

  24. Hubel D.H., Wiesel T.N.: Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. J. Physiol. 160, 106–154 (1962)

    Google Scholar 

  25. Grigorescu S.E., Petkov N., Kruizinga P.: Comparison of texture features based on Gabor filters. IEEE Trans. Image Process 11(10), 1160–1167 (2002)

    Article  MathSciNet  Google Scholar 

  26. Horapong, K., Thainimit, S., Areekul, V.: Iris texture analysis with polar based filtering: preliminary results. In: Proceedings of the First Electrical Engineering/Electronics, Computer, Telecommunications, and Information Technology (ECTI) Annual Conference, 13–14 May, pp. 250–253 (2004)

  27. Lee C.J., Wang S.D.: Fingerprint feature reduction by principal Gabor basis function. Pattern Recognit. 34(11), 2245–2248 (2001)

    Article  MATH  Google Scholar 

  28. Serre, T., Wolf, L., Poggio, T.: Object recognition with features inspired by visual cortex. In: CVPR, San Diego, June 2005

  29. Mutch, J., Lowe, D.G.: Multiclass object recognition with sparse, localized features. In: CVPR, New York, June, pp. 11–18 (2006)

  30. Hubel D.H., Wiesel T.: Receptive fields of single neurons in the cat’s striate cortex. J. Physiol. 148, 574–591 (1959)

    Google Scholar 

  31. Perrett D.I., Hietanen J.K., Oram M.W., Benson P.J.: Organization and functions of cells responsive to faces in the temporal cortex. Philos. Trans. R. Soc. Lond. 335, 23–30 (1992)

    Article  Google Scholar 

  32. Fukushima K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980)

    Article  MATH  Google Scholar 

  33. Fukushima K., Wake N.: Handwritten alphanumeric character recognition by neocognition. IEEE Trans. Neural Netw. 2(3), 355–365 (1991)

    Article  Google Scholar 

  34. LeCun Y., Bottou L., Bengio Y., Haffner Y.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)

    Article  Google Scholar 

  35. Rolls E.T., Deco G.: The computational neuroscience of vision. Oxford University Press, New York (2001)

    Google Scholar 

  36. Khosravi H., Kabir E.: Introducing a very large dataset of handwritten Farsi digits and a study on their varieties. Pattern Recognit. Lett. 28(10), 1133–1141 (2007)

    Article  Google Scholar 

  37. Oberhoff D., Kolesnik M.: Unsupervised shape learning in a neuromorphic hierarchy. Pattern Recognit. Image Anal. 18(2), 314–322 (2008)

    Article  Google Scholar 

  38. Ranzato, M., Huang, F.J., Boureau Y.L., LeCun, Y.: Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: Proceedings of the IEEE Computer Vision and Pattern Recognition Conference (CVPR’07) (2007)

  39. Keysers D., Deselaers T., Gollan C., Ney H.: Deformation models for image recognition. IEEE Trans. Pattern Anal. Mach. Intell. 29(8), 1422–1435 (2007)

    Article  Google Scholar 

  40. Belongie S., Malik J., Puzicha J.: Shape matching and object recognition using shape context. IEEE Trans. Pattern Anal. Mach. Intell. 24(24), 509–522 (2002)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Mandana Hamidi.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Hamidi, M., Borji, A. Invariance analysis of modified C2 features: case study—handwritten digit recognition. Machine Vision and Applications 21, 969–979 (2010). https://doi.org/10.1007/s00138-009-0216-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00138-009-0216-9

Keywords

Navigation