Skip to main content
SpringerLink
Log in

Robust Handwritten Character Recognition with Features Inspired by Visual Ventral Stream

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

This paper focuses on the applicability of the features inspired by the visual ventral stream for handwritten character recognition. A set of scale and translation invariant C2 features are first extracted from all images in the dataset. Three standard classifiers kNN, ANN and SVM are then trained over a training set and then compared over a separate test set. In order to achieve higher recognition rate, a two stage classifier was designed with different preprocessing in the second stage. Experiments performed to validate the method on the well-known MNIST database, standard Farsi digits and characters, exhibit high recognition rates and compete with some of the best existing approaches. Moreover an analysis is conducted to evaluate the robustness of this approach to orientation, scale and translation distortions.

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

Access this article

Log in via an institution

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. Fukushima K (1980) Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern 36(4): 193–202 doi:10.1007/BF00344251

    Article  MATH  Google Scholar 

  2. LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W et al. (1990) Handwritten digit recognition with a back-propagation network. In: Touretzky D (ed) Advances in Neural Information Processing Systems 2 (NIPS 89)

  3. Al-Omari FA, Al-Jarrah O (2004) Handwritten Indian numerals recognition system using probabilistic neural networks. Adv Eng Inform 18(1): 9–16 doi:10.1016/j.aei.2004.02.001

    Article  Google Scholar 

  4. Salah AA, Alpaydin E, Akarun L (2002) A selective attention-based method for visual pattern recognition with application to handwritten digit recognition and face recognition. IEEE Trans Pattern Anal Mach Intell 24(3): 420–425 doi:10.1109/34.990146

    Article  Google Scholar 

  5. Liu CL, Nakashima K, Sako H, Fujisawa H (2003) Handwritten digit recognition: Benchmarking of state-of-the-art techniques. Pattern Recognit 36(10): 2271–2285 doi:10.1016/S0031-3203(03)00085-2

    Article  MATH  Google Scholar 

  6. Shi M, Fujisawa Y, Wakabayashi T, Kimura F (2002) Handwritten numeral recognition using gradient and curvature of gray scale image. Pattern Recognit 35(10): 2051–2059 doi:10.1016/S0031-3203(01)00203-5

    Article  MATH  Google Scholar 

  7. Teow LN, Loe KF (2002) Robust vision-based features and classification schemes for off-line handwritten digit recognition. Pattern Recognit 35(11): 2355–2364 doi:10.1016/S0031-3203(01)00228-X

    Article  MATH  Google Scholar 

  8. Cheung K, Yeung D, Chin RT (1998) A Bayesian framework for deformable pattern recognition with application to handwritten character recognition. IEEE Trans Pattern Anal Mach Intell 29(12): 1382–1388 doi:10.1109/34.735813

    Article  Google Scholar 

  9. Tsang IJ, Tsang IR, Dyck DV (1998). Handwritten character recognition based on moment features derived from image partition. In: International conference on image processing, vol 2, pp 939–942

  10. Soltanzadeh H, Rahmati M (2004) Recognition of Persian handwritten digits using image profiles of multiple orientations. Pattern Recognit Lett 25(14): 1569–1576 doi:10.1016/j.patrec.2004.05.014

    Article  Google Scholar 

  11. Said FN, Yacoub RA, Suen CY (1999). 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

  12. Sadri J, Suen CY, Bui TD (2003) Application of support vector machines for recognition of handwritten Arabic/Persian digits. In: Second Iranian conference on machine vision and image processing, vol 1, pp 300–307

  13. Khosravi H, Kabir E (2007) Introducing a very large dataset of handwritten Farsi digits and a study on their varieties. Pattern Recognit Lett 28(10): 1133–1141 doi:10.1016/j.patrec.2006.12.022

    Article  Google Scholar 

  14. Dehghan M, Faez K, Ahmadi M, Shridhar M (2001) Handwritten Farsi (Arabic) word recognition: a holistic approach using discrete HMM. Pattern Recognit 34(5): 1057–1063 doi:10.1016/S0031-3203(00)00051-0

    Article  MATH  Google Scholar 

  15. Kouh M, Riesenhuber M (2003) Investigating Shape Representation in Area V4 with HMAX: orientation and grating selectivities. CBCL Paper #231/AIM #2003-021, Massachusetts Institute of Technology, Cambridge, MA

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

  17. Knoblich U, Bouvrie J, Poggio T (2007) Biophysical models of neural computation: max and tuning circuits. CBCL paper, Cambridge, MA

    Google Scholar 

  18. Quiroga RQ, Reddy L, Kreiman G, Koch C, Fried I (2005) Invariant visual representation by single neurons in the human brain. Nature 435: 1102–1107 doi:10.1038/nature03687

    Article  Google Scholar 

  19. Serre T, Oliva A, Poggio T (2007) A feedforward architecture accounts for rapid categorization. Proc Natl Acad Sci USA 104(15):6424–6429. PNAS. doi:10.1073/pnas.0700622104

    Google Scholar 

  20. Serre T, Wolf L, Bileschi S, Riesenhuber M, Poggio T (2007) Object recognition with cortex like mechanisms. IEEE Trans Pattern Anal Mach Intell 29(3): 411–426 doi:10.1109/TPAMI.2007.56

    Article  Google Scholar 

  21. Gabor D (1946) Theory of communication. J Inst Electr Eng 93(26): 429–457

    Google Scholar 

  22. Hubel D, Wiesel T (1965) Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) of the cat. J Neurophysiol 28: 229–289

    Google Scholar 

  23. Serre T, Riesenhuber M (2004) Realistic modeling of simple and complex cell tuning in the hmax model, and implications for invariant object recognition in cortex. Technical Report CBCL Paper 239/AI Memo 2004- 017, Massachusetts Institute of Technology, Cambridge, MA

  24. Serre T, Wolf L, Poggio T (2004) A new biologically motivated framework for robust object recognition. Technical Report CBCL Paper 243/AI Memo 2004- 026, Massachusetts Institute of Technology, Cambridge, MA

  25. Keysers D, Deselaers T, Gollan C, Ney H (2007) Deformation models for image recognition. IEEE Trans Pattern Anal Mach Intell 29(8): 1422–1435 doi:10.1109/TPAMI.2007.1153

    Article  Google Scholar 

  26. Zhang P, Bui TD, Suen CY (2007) A novel hierarchical ensemble classifier system with a high recognition performance on handwritten digits. Pattern Recognit 40(12): 3415–3429 doi:10.1016/j.patcog.2007.03.022

    Article  MATH  Google Scholar 

  27. Marc’Aurelio R, Poultney C, Chopra C, LeCun Y (2006) Efficient learning of sparse representations with an energy-based model. In: Platt J et al (eds) Advances in Neural Information Processing Systems (NIPS 2006). MIT Press

  28. Kussul EM, Baidyk TN, Wunsch DC II, Makeyev O, Martin A (2006) Permutation coding technique for image recognition systems. IEEE Trans Neural Netw 17(6): 1566–1579 doi:10.1109/TNN.2006.880676

    Article  Google Scholar 

  29. LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11): 2278–2324 doi:10.1109/5.726791

    Article  Google Scholar 

  30. Rumelhart DE, McClelland JL (1986) Parallel distributed processing, vol 1 & 2. MIT, Cambridge

    Google Scholar 

  31. Vapnik VN (1995) The nature of statistical learning theory. Springer-Verlag, NewYork

    MATH  Google Scholar 

  32. Serre T, Wolf L, Poggio T (2005) Object recognition with features inspired by visual cortex. In: Proceedings of IEEE conference computer vision and pattern recognition, Massachusetts Institute of Technology

  33. Dehghan M, Faez K (1997) Farsi handwritten character recognition with moment invariants. In: Proceedings of the 13th international conference of digital signal processing, vol 2, issues 2–4, pp 507–510

Download references

Author information

Authors and Affiliations

  1. School of Cognitive Sciences, Institute for Studies in Theoretical Physics and Mathematics, Niavaran Bldg., P. O. Box 19395-5746, Tehran, Iran

    Ali Borji

  2. Computer and Information Technology Department, Azad University Branch of Zarghan, Booali Boulevard, Azad University Street, P. O. Box 73415-314, Zarghan, Iran

    Mandana Hamidi

  3. Computer, Engineering and Information Technology Department, Azad University Branch of Qazvin, Qazvin, Iran

    Fariborz Mahmoudi

Authors
  1. Ali Borji
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mandana Hamidi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fariborz Mahmoudi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ali Borji.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Borji, A., Hamidi, M. & Mahmoudi, F. Robust Handwritten Character Recognition with Features Inspired by Visual Ventral Stream. Neural Process Lett 28, 97–111 (2008). https://doi.org/10.1007/s11063-008-9084-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11063-008-9084-y

Keywords

Search

Navigation