Abstract
This paper introduces an expert system for handwritten digit recognition. The system considers that a numeric handwritten character can be decomposed into vertical and horizontal strokes. Then, the positions where horizontal strokes are connected to the vertical strokes are extracted as features using dynamic zoning. These features are laid into a representative string which is validated by a regular expression following a matching pattern. The knowledge base is constructed from a decision tree structure that stores all well-formatted representative strings with the digits definitions. Finally, the inference engine tries to match unknown digits with the trained knowledge base in order to achieve the recognition. The promising results obtained by testing the system on the well-known MNIST handwritten database are compared with other approaches for corroborating its effectiveness.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
References
Ahmed, M., Ward, K.R.: An expert system for general symbol recognition. Pattern Recognit. 33, 1975–1988 (2000)
Alonso, A., Fernández, R.A., García, I.: Recognition of merged characters based on vertical strokes and adjacency regions. V Congress of Hispalinux (2005)
Bertolami, R., Bertolami, R., Uchida, S., Uchida, S., Zimmermann, M., Zimmermann, M., Bunke, H., Bunke, H.: Non-uniform slant correction for handwritten text line recognition. In: ICDAR 2007, pp. 18–22 (2007). http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=4378668
Batista, B.L., Gomes, M.H., Herbster, F.R.: Application of growing hierarchical self-organizing map in handwritten digit recognition. In: Brazilian Symposium on Computer Graphics and Image Processing, pp. 1539–1545 (2003)
Chen, W., Liao, Y., Chen, S.: Speech recognition with hierarchical recurrent neural networks. Pattern Recognit. 28(6), 795–805 (1995). http://www.sciencedirect.com/science/article/pii/003132039400145C
De Marsico, M., Nappi, M., Riccio, D., Wechsler, H.: Robust face recognition after plastic surgery using region-based approaches. Pattern Recognit. 48(4), 1261–1276 (2015). http://www.sciencedirect.com/science/article/pii/S0031320314003884
Ha, T.M., Zimmermann, M., Bunke, H.: Off-line handwritten numeral string recognition by combining segmentation-based and segmentation-free methods. Pattern Recognit. 31(3), 257–272 (1998). http://www.sciencedirect.com/science/article/pii/S0031320397000502
Haji, M., Bui, T.D., Suen, C.Y.: Removal of noise patterns in handwritten images using expectation maximization and fuzzy inference systems. Pattern Recognit. 45(12), 4237–4249 (2012). http://linkinghub.elsevier.com/retrieve/pii/S0031320312002439
Hanmandlu, M., Mohan, M.K., Chakraborty, S., Goyal, S., Choudhury, D.: Unconstrained handwritten character recognition based on fuzzy logic. Pattern Recognit. 36(3), 603–623 (2003). http://www.sciencedirect.com/science/article/pii/S0031320302000699
Impedovo, D., Pirlo, G.: Zoning methods for handwritten character recognition: a survey. Pattern Recognit. 47(3), 969–981 (2014). http://linkinghub.elsevier.com/retrieve/pii/S0031320313002458
Jiang, D., Mekonnen, T.M., Merkebu, T.E., Gebrehiwot, A.: Car plate recognition system. In: 2012 Fifth International Conference on Intelligent Networks and Intelligent Systems, pp. 9–12 (2012). http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6376472
Kessentini, Y., Paquet, T., Hamadou, A.: Off-line handwritten word recognition using multi-stream hidden markov models. Pattern Recognit. Lett. 31(1), 60–70 (2010). http://www.sciencedirect.com/science/article/pii/S0167865509002232
Kundu, A., He, Y., Bahl, P.: Recognition of handwritten word: first and second order hidden markov model based approach. Pattern Recognit. 22(3), 283–297 (1989). http://www.sciencedirect.com/science/article/pii/0031320389900769
Li, H., Greenspan, M.: Model-based segmentation and recognition of dynamic gestures in continuous video streams. Pattern Recognit. 44(8), 1614–1628 (2011). http://www.sciencedirect.com/science/article/pii/S0031320310005807
Liu, C.L., Nakashima, K., Sako, H., Fujisawa, H.: Handwritten digit recognition: investigation of normalization and feature extraction techniques. Pattern Recognit. 37(2), 265–279 (2004). http://linkinghub.elsevier.com/retrieve/pii/S0031320303002243
Lü, H.E., Wang, P.S.P.: A comment on a fast parallel algorithm for thinning digital patterns. Commun. ACM 29(3), 239–242 (1986)
Álvarez, D., Fernández, R., Sánchez, L.: Stroke based handwritten character recognition. In: Corchado, E., Snášel, V., Abraham, A., Woźniak, M., Graña, M., Cho, S.-B. (eds.) HAIS 2012, Part I. LNCS, vol. 7208, pp. 343–351. Springer, Heidelberg (2012)
Morita, M., Letelier, E.: Recognition of handwritten dates on bank checks using an HMM approach. In: Proceedings of XIII Brazilian Symposium on Computer Graphics and Image Processing, pp. 113–120 (2000). http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=883903
Oh, I.S., Suen, C.Y.: A class-modular feedforward neural network for handwriting recognition. Pattern Recognit. 35(1), 229–244 (2002). http://linkinghub.elsevier.com/retrieve/pii/S0031320300001813
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. B Cybern. SMC 9(1), 62–66 (1979). http://web-ext.u-aizu.ac.jp/course/bmclass/documents/otsu1979.pdf
Palacios, R., Gupta, A.: Training neural networks for reading handwritten amounts on checks. In: 2003 IEEE 13th Workshop on Neural Networks for Signal Processing, NNSP 2003, pp. 607–616 (2003)
Ping, Z., Lihui, C.: A novel feature extraction method and hybrid tree classification for handwritten numeral recognition. Pattern Recognit. Lett. 23(13), 45–56 (2002). http://www.sciencedirect.com/science/article/pii/S0167865501000885
Shah-Hosseini, H.: Binary tree time adaptive self-organizing map. Neurocomputing 74(11), 1823–1839 (2011). http://www.sciencedirect.com/science/article/pii/S0925231211000786
Sun, C., Si, D.: Skew and slant correction for document images using gradient direction. In: Proceedings of the Fourth International Conference on Document Analysis and Recognition, vol. 1, pp. 142–146 (1997)
Trier, D., Jain, A., Taxt, T.: Feature extraction methods for character recognition-a survey. Pattern Recognit. 29(4), 641–662 (1996). http://www.sciencedirect.com/science/article/pii/0031320395001182
Vamvakas, G., Gatos, B., Perantonis, S.: Handwritten character recognition through two-stage foreground sub-sampling. Pattern Recognit. 43(8), 2807–2816 (2010). http://www.sciencedirect.com/science/article/pii/S0031320310000968
Wakahara, T., Yamashita, Y.: k-nn classification of handwritten characters via accelerated GAT correlation. Pattern Recognit. 47(3), 994–1001 (2014)
Zeeuw, F.: Slant correction using histograms. Bachelors thesis in Artificial Intelligence, pp. 1–10 (2006)
Zou, Y., Dong, F., Lei, B., Sun, S., Jiang, T., Chen, P.: Maximum similarity thresholding. Digit. Signal. Process. 1, 1–16 (2014). http://linkinghub.elsevier.com/retrieve/pii/S1051200414000451
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Álvarez, D., Fernández, R., Sánchez, L., Alija, J. (2015). Expert System for Handwritten Numeral Recognition Using Dynamic Zoning. In: Onieva, E., Santos, I., Osaba, E., Quintián, H., Corchado, E. (eds) Hybrid Artificial Intelligent Systems. HAIS 2015. Lecture Notes in Computer Science(), vol 9121. Springer, Cham. https://doi.org/10.1007/978-3-319-19644-2_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-19644-2_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19643-5
Online ISBN: 978-3-319-19644-2
eBook Packages: Computer ScienceComputer Science (R0)