Skip to main content
SpringerLink
Log in

Use of wavelet-based two-dimensional scaling moments and structural features in cascade neuro-fuzzy classifiers for handwritten digit recognition

  • Review
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

In this paper, a novel handwritten digit recognition system is proposed. The system consist of feature extraction, feature selection and classification stages. The features of digits are extracted by using the moment-based and structural-based methods. For the moment-based method, wavelet-based two-dimensional scaling moments (2-DSMs), which have uniquely different angular divisions of polar form, are considered. The structural-based features including profiles, intersections of horizontal and vertical straight lines, concavity, number and location of holes are used. In the feature selection stage, Fisher’s linear discriminant analysis is used to obtain the discriminative features. The feature selection is performed to improve not only the processing time but also recognition rates. In the classification stage, the digits are classified by neuro-fuzzy classifiers (NFCs). A three-stage cascade NFCs with rejection strategy is used in the system to improve the misclassification rate for the handwritten digit recognition task. The experiments are performed on the MNIST and USPS handwritten digit databases. The high correct classification rates of 98.72 % for MNIST and 97.21 % for USPS are attained by using only one hundred robust hybrid features and cascade NFCs. The experiments showed that the proposed system yields better results among those systems that use only moment-based features.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Liu CL, Nakashima K, Sako H, Fujisawa H (2003) Handwritten digit recognition: benchmarking of state-of-the-art techniques. Pattern Recogn 36(10):2271–2285

    Article  MATH  Google Scholar 

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

    Article  Google Scholar 

  3. Teow LN, Loe KF (2002) Robust vision-based features and classification schemes for off-line handwritten digit recognition. Pattern Recogn 35(11):2355–2364

    Article  MATH  Google Scholar 

  4. Niu XX, Suen CY (2012) A novel hybrid CNN–SVM classifier for recognizing handwritten digits. Pattern Recogn 45(4):1318–1325

    Article  Google Scholar 

  5. Zhang P, Bui TD, Suen CY (2007) A novel cascade ensemble classifier system with a high recognition performance on handwritten digits. Pattern Recogn 40:3415–3429

    Article  MATH  Google Scholar 

  6. Nguyen MH, de la Torre F (2010) Optimal feature selection for support vector machines. Pattern Recogn 43(3):584–591

    Article  MATH  Google Scholar 

  7. Zhang P, Bui TD, Suen CY (2005) Hybrid feature extraction and feature selection for improving recognition accuracy of handwritten numerals. In: Proceedings of the 2005 8th international conference on document analysis and recognition, vol 1, pp 136–140

  8. Tan CC, Eswaran C (2010) Reconstruction and recognition of face and digit images using autoencoders. Neural Comput Appl 19(7):1069–1079

    Article  Google Scholar 

  9. Goltsev A, Gritsenko V (2009) Modular neural networks with Hebbian learning rule. Neurocomputing 72(10–12):2477–2482

    Article  Google Scholar 

  10. Lauer F, Suen CY, Bloch G (2007) A trainable feature extractor for handwritten digit recognition. Pattern Recogn 40(6):1816–1824

    Article  MATH  Google Scholar 

  11. Heutte L, Paquet T, Moreau JV, Lecourtier Y, Olivier C (1998) A structural/statistical feature based vector for handwritten character recognition. Pattern Recogn Lett 19:629–641

    Article  Google Scholar 

  12. Kan C, Srinath MD (2002) Invariant character recognition with Zernike and orthogonal Fourier-Mellin moments. Pattern Recogn 35(1):143–154

    Article  MATH  Google Scholar 

  13. Yadav RB, Nishchal NK, Gupta AK, Rastogi VK (2008) Retrieval and classification of objects using generic Fourier, Legendre moment, and wavelet Zernike moment descriptors and recognition using joint transform correlator. Opt Laser Technol 40(3):517–527

    Article  Google Scholar 

  14. Shen D, Ip HHS (1999) Discriminative wavelet shape descriptors for recognition of 2-D patterns. Pattern Recogn 32(2):151–165

    Article  Google Scholar 

  15. Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford

  16. Gunal S, Edizkan R (2008) Subspace based feature selection for pattern recognition. Inf Sci 178:3716–3726

    Article  Google Scholar 

  17. Liu CL, Sako H, Fujisawa H (2004) Discriminative learning quadratic discriminant function for handwriting recognition. IEEE Trans Neural Netw 15(2):430–444

    Article  Google Scholar 

  18. Zhang B, Srihari SN (2004) Fast k-nearest neighbor classification using cluster-based trees. IEEE Trans Pattern Anal Mach Intell 26(4):525–528

  19. Likforman-Sulem L, Sigelle M (2008) Recognition of degraded characters using dynamic Bayesian networks. Pattern Recogn 41(10):3092–3103

    Article  MATH  Google Scholar 

  20. Kusy M, Szczepanski D (2012) Influence of graphical weights’ interpretation and filtration algorithms on generalization ability of neural networks applied to digit recognition. Neural Comput Appl 21(7):1783–1790

    Article  Google Scholar 

  21. Dong JX, Krzyzak A, Suen CY (2005) Fast SVM training algorithm with decomposition on very large data sets. IEEE Trans Pattern Anal Mach Intell 27(4):603–618

  22. Angelov P, Lughofer E, Zhou X (2008) Evolving fuzzy classifiers using different model architectures. Fuzzy Sets Syst 159(23):3160–3182

    Article  MATH  MathSciNet  Google Scholar 

  23. Kaburlasos VG, Papadakis SE (2009) A granular extension of the fuzzy-ARTMAP (FAM) neural classifier based on fuzzy lattice reasoning (FLR). Neurocomputing 72(10–12):2067–2078

    Article  Google Scholar 

  24. Cetişli B (2005) Handwritten character recognition: classification of the wavelet moment features using modified ANFIS. Ph. D. thesis, Institute of Natural and Applied Sciences, Eskişehir Osmangazi University

  25. Liu CL, Nakashima K, Sako H, Fujisawa H (2004) Handwritten digit recognition: investigation of normalization and feature extraction techniques. Pattern Recogn 37:265–279

    Article  MATH  Google Scholar 

  26. Papakostas GA, Boutalis YS, Karras DA, Mertzios BG (2009) Pattern classification by using improved wavelet compressed Zernike moments. Appl Math Comput 212(1):162–176

    Article  MATH  MathSciNet  Google Scholar 

  27. Zhao C, Miao D, Lai Z et al (2013) Two-dimensional color uncorrelated discriminant analysis for face recognition. Neurocomputing 113:251–261

    Article  Google Scholar 

  28. Jang JSR, Sun CT, Mizutani E (1997) Neuro-fuzzy and soft computing. Prentice Hall, Upper Saddle River

  29. Sun CT, Jang JSR (1993) A neuro-fuzzy classifier and its applications. In: Proceedings of IEEE international conference on fuzzy systems, San Francisco

  30. Cetişli B, Barkana A (2010) Speeding up the scaled conjugate gradient algorithm and its application in neuro-fuzzy classifier training. Soft Comput 14(4):365–378

    Article  MATH  Google Scholar 

  31. MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist/. Last accessed 24 March 2013

  32. Schölkopf B (2010) The USPS data set. ftp://www.kyb.tuebingen.mpg.de/pub/bs/data/

  33. Goltsev A, Rachkovskij D (2005) Combination of the assembly neural network with a perceptron for recognition of handwritten digits arranged in numeral strings. Pattern Recogn 38(3):315–322

    Article  MATH  Google Scholar 

  34. Karic M, Martinovic G (2013) Improving offline handwritten digit recognition using concavity-based features. Int J Comput Commun Control 8(2):2209–2234

  35. Hua Q, Bai L, Wang X, Liu Y (2012) Local similarity and diversity preserving discriminant projection for face and handwriting digits recognition. Neurocomputing 86:150–157

    Article  Google Scholar 

  36. Zhao C, Lai Z, Liu C, Gu X, Qian J (2012) Fuzzy local maximal marginal embedding for feature extraction. Soft Comput 16:77–87

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Engineering, Süleyman Demirel University, 32260, Isparta, Turkey

    Bayram Cetişli

  2. Department of Electrical and Electronics Engineering, Eskişehir Osmangazi University, Bati-Meselik, 26480, Eskisehir, Turkey

    Rifat Edizkan

Authors
  1. Bayram Cetişli
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rifat Edizkan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bayram Cetişli.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Cetişli, B., Edizkan, R. Use of wavelet-based two-dimensional scaling moments and structural features in cascade neuro-fuzzy classifiers for handwritten digit recognition. Neural Comput & Applic 26, 613–624 (2015). https://doi.org/10.1007/s00521-014-1758-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-014-1758-y

Keywords

Search

Navigation