Skip to main content
Log in

Handwritten characters recognition based on nature-inspired computing and neuro-evolution

Applied Intelligence Aims and scope Submit manuscript

Abstract

The enormous services obtainable by bank and postal systems are not 100 % guaranteed due to variability of handwriting styles. Various methods based on neural networks have been suggested to address this issue. Unfortunately, they often fall into local optima that arises from the use of old learning methods. Global optimization methods provided new directions for neural networks evolution that may be useful in recognition. This paper develops efficient algorithms that compute globally optimal solutions by exploiting the benefits of both swarm intelligence and neuro-evolution in a way to improve the overall performance of a character recognition system. Various adaptations implied to both MLP and RBF networks have been suggested namely: particle swarm optimization (PSO) and the bees algorithm (BA) for characters classification, MLP training or RBF design by co-evolution and effective combinations of MLPs, RBFs or SVMs as an attempt to overcome the drawbacks of old recognition methods. Results proved that networks combination proposals ensure the highest improvement compared to either standard MLP and RBF networks, the co-evolutionary alternatives or other classifiers combination based on common combination rules namely majority voting, the fusion rules of min, max, sum, average, product and Bayes, Decision template and the Behavior Knowledge Space (BKS).

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

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

Similar content being viewed by others

References

  1. Abraham A (2004) Meta-learning evolutionary artificial neural networks. Neurocomput J 56c:1–38

    Google Scholar 

  2. Abraham A, Nath B (2000) Optimal design of neural nets using hybrid algorithms. In: Proceedings of 6th Pacific Rim international conference on artificial intelligence. Springer, Berlin, pp 510–520

    Google Scholar 

  3. Abraham A, Steinberg D (2001) Is neural network a reliable forecaster on Earth? A MARS query! Lect Notes Comput Sci 2085:679–686

    Article  Google Scholar 

  4. Ajith A (2002) Optimization of evolutionary neural networks using hybrid learning algorithms. In: IEEE 2002 joint international conference on neural networks. IEEE Press, New York, pp 2797–2802

    Google Scholar 

  5. Angeline PJ (1997) Evolving basis functions with dynamic receptive fields. In: Proc 1997 IEEE int conf systems, man, and cybernetics, Part 5 (of 5), pp 4109–4114

    Chapter  Google Scholar 

  6. Ben Ali YM (2012) Psychological model of particle swarm optimization based multiple emotions. Appl Intell 36(3):649–663

    Article  Google Scholar 

  7. Binos T (2002) Evolving neural network architecture and weights using an evolutionary algorithm. Minor Thesis, RMIT Dept of Comp Sci

  8. Canuto AMP, Santos AM, Vargas RR (2011) Ensembles of ARTMAP-based neural networks: an experimental study. Appl Intell 35(1):1–17

    Article  Google Scholar 

  9. Carcenac M (2009) A modular neural network for super-resolution of human faces. Appl Intell 30(2):168–186

    Article  Google Scholar 

  10. Cartlidge JP (2004) Rules of engagement: competitive coevolutionary dynamics in computational systems. PhD thesis

  11. Cordella L, De Stefano C, Fontanella F, Marrocco C (2008) A feature selection algorithm for handwritten character recognition. In: International conference on pattern recognition—ICPR, pp 1–4

    Google Scholar 

  12. Dileep Gaurav D Feature extraction for character recognition. http://www.mathworks.com/matlabcentral/fileexchange/24624-feature-extraction-for-character-recognition

  13. Eberhart RC, Shi Y (2000) Comparing inertia weights and constriction factors in particle swarm optimization. In: Proceedings of the congress on evolutionary computation, pp 84–88

    Google Scholar 

  14. El Fadili H, Zenkouar K, Qjidaa H (2005) Evolving neural networks using moment method for handwritten digit recognition. In: Engineering and technology

    Google Scholar 

  15. Frank A, Asuncion A (2010) UCI machine learning repository. University of California, School of Information and Computer Science, Irvine, CA. http://archive.ics.uci.edu/ml

  16. Gagné C, Parizeau M (2006) Genetic engineering of hierarchical fuzzy regional representations for handwritten character recognition. Int J Doc Anal Recognit 8(4):223–231

    Article  Google Scholar 

  17. Gagnon T, Lefebvre R (2003) A neural-network approach for pre-classification in musical chords recognition. In: Proc. 37th Asilomar conference on signals, systems and computers, Asilomar, Pacific Grove, November 9–12

    Google Scholar 

  18. Gallinari P, Cibas T (1999) Practical complexity control in multilayer perceptrons. Signal Process 74(1):29–46

    Article  MATH  Google Scholar 

  19. Ghosh R, Ghosh M (2005) An intelligent offline handwriting recognition system using evolutionary neural learning algorithm and rule based over segmented data points. J Res Pract Inf Technol 37(1)

  20. Guangmin S, Zhang C, Weiwei Z, Guangyu Y (2010) A new recognition method of vehicle license plate based on genetic neural network. In: 5th IEEE conference on industrial electronics and applications, pp 1662–1666

    Google Scholar 

  21. http://yann.lecun.com/exdb/mnist/

  22. Janzen DH (1980) When is it co-evolution? Evolution 34(3):611–612

    Article  Google Scholar 

  23. Kala R, Vazirani H, Khawalkar N, Bhattacharya M (2010) Evolutionary radial basis function network for classificatory problems. Int J Comput Sci Appl 7(4):34–49

    Google Scholar 

  24. Kang J, Kim S, An S-Y, Oh S-Y (2012) A new approach to simultaneous localization and map building with implicit model learning using neuro evolutionary optimization. Appl Intell 36(1):242–269

    Article  Google Scholar 

  25. Kaur R, Singh B (2011) A hybrid neural approach for character recognition system. Int J Comput Sci Inf Technol 2(2):721–726

    Google Scholar 

  26. Kessler J, Rasheed K, Arpinar IB (2007) Using genetic algorithms to reorganize superpeer structure in peer to peer networks. Appl Intell 26(1):35–52

    Article  Google Scholar 

  27. Khan SA, Engelbrecht AP (2012) A fuzzy particle swarm optimization algorithm for computer communication network topology design. Appl Intell 36(1):161–177

    Article  Google Scholar 

  28. Kim K, Ahn H (2012) Simultaneous optimization of artificial neural networks for financial forecasting. Appl Intell 36(4):887–898

    Article  MathSciNet  Google Scholar 

  29. Kunte RS, Sudhaker Samuel RD (2007) A simple and efficient optical character recognition system for basic symbols in printed Kannada text. Sadhana 32(5):521–533

    Article  Google Scholar 

  30. Kwasnicka H, Paradowski M (2005) Efficiency aspects of neural network architecture evolution using direct and indirect encoding. In: Ribeiro B (ed) Adaptive and natural computing algorithms. Proceedings of the international conference. Coimbra, Portugal, March 21–23, 2005. Springer, New York, pp 405–408.

    Chapter  Google Scholar 

  31. LeCun Y, Matan O, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD, Baird HS (1990) Handwritten zip code recognition with multilayer networks. In: Proc of the international conference on pattern recognition, vol. II. IEEE, Atlantic City, pp 35–40, invited paper

    Chapter  Google Scholar 

  32. LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1992) Handwritten digit recognition with a back-propagation network. In: Lisboa PGJ (ed) Neural networks, current applications. Chapman and Hall, London

    Google Scholar 

  33. Li Y, Li J, Li M (2006) Character recognition based on hierarchical RBF neural networks. In: Proceedings of ISDA (1), pp 127–132

    Google Scholar 

  34. Maillard EP, Gueriot D (1997) RBF neural network, basis functions and genetic algorithms. In: Proc 1997 IEEE int conf neural networks. Part 4 (of 4), pp 2187–2190

    Google Scholar 

  35. Mangal M, Singh MP (2006) Handwritten English vowels recognition using hybrid evolutionary feed-forward neural network. Malays J Comput Sci 19(2)

  36. Nebti S, Boukerram A (2010) Use of nature-inspired meta-heuristics for handwritten digits recognition. Int J Comput Linguist Res 1(1)

  37. Nebti S, Boukerram A (2010) An improved radial basis function neural network based on a cooperative coevolutionary algorithm for handwritten digits recognition. In: ICMWI, pp 464–468

    Google Scholar 

  38. Ni DX (2007) Application of neural networks to character recognition. In: Proceedings of students/faculty research day, CSIS, Pace University, May 4th

    Google Scholar 

  39. Oliveira LS, Bortolozzi F, Suen CY (2001) Automatic recognition of handwritten numerical strings: a recognition and verification strategy. IEEE Trans Pattern Recogn Mach Intell 24(11):1448–1456

    Google Scholar 

  40. Oliveira LS, de Souza Britto A Jr, Sabourin R (2005) Improving cascading classifiers with particle swarm optimization. In: Proceedings of ICDAR’2005, pp 570–574

    Google Scholar 

  41. Paredis J, Westra R (1997) Coevolutionary computation for path planning. In: Zimmermann H-J (ed) Proceedings 5th European congress on intelligent techniques and soft computing. Verlag Mainz, Aachen

    Google Scholar 

  42. Park J (1999) Hierarchical character recognition and its uses in handwritten word/phrase recognition. PhD thesis

  43. Parker JR (1993) Practical computer vision using C. Wiley, New York, p 476

    MATH  Google Scholar 

  44. Pham DT, Ghanbarzadeh A, Koc E, Otri S, Rahim S, Zaidi M (2005) The bees algorithm. Technical Note, Manufacturing Engineering Centre, Cardiff University, UK

  45. Pham DT, Ghanbarzadeh A, Koç E, Otri S, Rahim S, Zaidi M (2006) The bees algorithm—a novel tool for complex optimisation problems. In: Proceedings of IPROMS 2006 conference, pp 454–461

    Google Scholar 

  46. Pham DT, Koç E, Lee JY, Phrueksanant J (2007) Using the bees algorithm to schedule jobs for a machine. In: Proc eighth international conference on laser metrology, CMM and machine tool performance, LAMDAMAP, Euspen, UK, Cardiff, pp 430–439

    Google Scholar 

  47. Potter MA, De Jong KA (1994) A cooperative coevolutionary approach to function optimisation. In: Davidor Y, Schwefel H-P, Männer R (eds) Parallel problem solving from nature III. Springer, Berlin, pp 249–257

    Chapter  Google Scholar 

  48. Quost B, Denoeux T, Masson M (2006) One-against-all combination in the framework of belief functions. In: Proceedings of IPMU’2006, vol. I, Paris, France, July, pp 356–363

    Google Scholar 

  49. Ross BJ, Zuviria E (2007) Evolving dynamic Bayesian networks with multi-objective genetic algorithms. Appl Intell 26(1):13–23

    Article  Google Scholar 

  50. Sabri AM, Wasfi GA (2011) Recognition of Arabic (Indian) bank check digits using log-Gabor filters. Appl Intell 35(3):445–456

    Article  Google Scholar 

  51. Shin KS, Jeong Y, Jeong MK (2012) A two-leveled symbiotic evolutionary algorithm for clustering problems. Appl Intell 36(4):788–799

    Article  Google Scholar 

  52. Shuang B, Chen J, Li Z (2011) Study on hybrid PS-ACO algorithm. Appl Intell 34(1):64–73

    Article  Google Scholar 

  53. Silva AF, Silva AP, Costa E (2003) SAPPO: a simple, adaptive, predator prey optimiser. In: Proc of the 11th Portuguese conference on artificial intelligence, workshop on artificial life and evolutionary algorithms (ALEA), EPIA’03, Beja, Portugal, December

    Google Scholar 

  54. Simila T, Tikka J (2009) Combined input variable selection and model complexity control for nonlinear regression. Pattern Recognit Lett 30(3)

  55. Valdovinos RM, Sanchez JS (2006) Ensembles of multilayer perceptron and modular neural networks for fast and accurate learning. In: MICAI ’06 proceedings of the fifth Mexican international conference on artificial intelligence, USA

    Google Scholar 

  56. Valova I, Milano G, Bowen K, Gueorguieva N (2011) Bridging the fuzzy, neural and evolutionary paradigms for automatic target recognition. Appl Intell 35(2):211–225

    Article  Google Scholar 

  57. Vasconcelos GC (1995) An investigation of feedforward neural networks with respect to the detection of spurious patterns. PhD Thesis

  58. Verma B, Hassan SZ (2011) Hybrid ensemble approach for classification. Appl Intell 34(2):258–278

    Article  Google Scholar 

  59. Villegas-Cortez J, Avilés-Cruz C (2005) Font recognition by invariant moments of global textures. In: Proceedings of international workshop VLBV05 (very low bit-rate video-coding 2005), 15–16 September

    Google Scholar 

  60. Wiegand RP (2004) Analysis of cooperative coevolutionary algorithms. PhD thesis, George Mason University

  61. Wu P, Shieh CS, Kao JH (2006) The development of neural network models by revised particle swarm optimization. In: JCIS-2006, pp 1951–6851

    Google Scholar 

  62. Yao X (1999) Evolving artificial neural networks. Proc IEEE 87(9):1423–1447

    Article  Google Scholar 

  63. Yao X (1999) Evolving artificial neural networks. Proc IEEE 87(9):1423–1447

    Article  Google Scholar 

  64. Zouari H (2004) Contribution à l’évaluation des méthodes de combinaison parallèle de classifieurs par simulation. PhD thesis, ROUEN University

  65. Zouari H, Heutte L, Lecourtier Y, Alimi A (2002) Un panorama des méthodes de combinaison de classificateurs en reconnaissance de formes. In: RFIA’2002, Angers, France, vol 2, pp 499–508

    Google Scholar 

  66. Zouari H, Heutte L, Lecourtier Y, Alimi A (2002) Un panorama des méthodes de combinaison de classifieurs en reconnaissance de formes. In: Reconnaissance de formes et intelligence artificielle (RFIA), pp 499–508

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Salima Nebti.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Nebti, S., Boukerram, A. Handwritten characters recognition based on nature-inspired computing and neuro-evolution. Appl Intell 38, 146–159 (2013). https://doi.org/10.1007/s10489-012-0362-z

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-012-0362-z

Keywords

Navigation