Skip to main content

Advertisement

SpringerLink
Log in

Handwritten character recognition using wavelet energy and extreme learning machine

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

This paper deals with the recognition of handwritten Malayalam character using wavelet energy feature (WEF) and extreme learning machine (ELM). The wavelet energy (WE) is a new and robust parameter, and is derived using wavelet transform. It can reduce the influences of different types of noise at different levels. WEF can reflect the WE distribution of characters in several directions at different scales. To a non oscillating pattern, the amplitudes of wavelet coefficients increase when the scale of wavelet decomposition increase. WE of different decomposition levels have different powers to discriminate the character images. These features constitute patterns of handwritten characters for classification. The traditional learning algorithms of the different classifiers are far slower than required. So we have used an extremely fast leaning algorithm called ELM for single hidden layer feed forward networks (SLFN), which randomly chooses the input weights and analytically determines the output weights of SLFN. This algorithm learns much faster than traditional popular learning algorithms for feed forward neural networks. This feature vector, classifier combination gave good recognition accuracy at level 6 of the wavelet decomposition.

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.

Fig. 1
Fig. 2

Similar content being viewed by others

References

  1. Santhosh KC, Nattee C (2009) A comprehensive survey on on-line handwriting recognition technology and its application to the Nepalese Natural Handwriting. Kathmandu Univ J Sci Eng Technol 5(1):31–55

    Google Scholar 

  2. Plotz T, Fink GA (2009) Markov models for offline handwriting recognition: a survey. Int J Document Anal Recogn 12:269–298

    Article  Google Scholar 

  3. Raju G (2008) Wavelet transform and projection profiles in handwritten character recognition—a performance analysis. In: Proceedings of International Conference on ADCOM, pp 309–313

  4. Plamondon R, Srihari SN (2000) On-line and off-line handwriting recognition: a comprehensive survey. IEEE Trans Pattern Anal Mach Intell 22(1):63–84

    Article  Google Scholar 

  5. Bhattacharya U, Chaudhuri BB (2009) Handwritten numeral databases of indian scripts and multistage recognition of mixed numerals. IEEE Trans Pattern Anal Mach Intell 31(3):444–457

    Article  Google Scholar 

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

    Article  MATH  Google Scholar 

  7. Kimura F, Miyake Y, Sridhar M (1995) Handwritten ZIP code recognition using Lexicon free word recognition algorithm. Proc Int Conf Document Anal Recogn 2:906–910

    Article  Google Scholar 

  8. Liu H, Ding X (2005) Handwritten character recognition using gradient feature and quadratic classifier with multiple discrimination schemes. In: Proceedings of International Conference on Document Analysis and Recognition, pp 19–25

  9. Shi M, Fujisawa Y, Wakabayashi T, Kimura F (2002) Handwritten numeral recognition using gradient and curvature of gray scale image. Pattern Recogn 35(10):2051–2059

    Article  MATH  Google Scholar 

  10. Shustorovich A (1994) A subspace projection approach to feature extraction: the 2D gabor transform for character recognition. Neural Netw 7(8):1295–1301

    Article  Google Scholar 

  11. Heutte L, Paquet T, Moreau JV, Lecourtier Y, Oliver C (1998) A structural/statistical feature based vector for handwritten character recognition. Pattern Recogn Lett 19(7):629–641

    Article  Google Scholar 

  12. Wu X-Q, Wang K-Q, Zhang D (2005) Wavelet energy feature extraction and matching for palmprint recognition. J Comput Sci Technol 20(3):411–418

    Article  MathSciNet  Google Scholar 

  13. Juang C-F, Cheng C-N, Chen T-M (2009) Speech detection in noisy environments by wavelet energy-based recurrent neural fuzzy network. Expert Syst Appl 36:321–332

    Article  Google Scholar 

  14. Huang G-B, Chen L, Siew C-K (2006) Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw 17(4):879–892

    Article  Google Scholar 

  15. Zhu Q-Y, Qin AK, Suganthan PN, Huang G-B (2005) Evolutionary extreme learning machine. Pattern Recogn 38:1759–1763

    Article  MATH  Google Scholar 

  16. Huang G-B, Zhu Q-Y, Siew C-K (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501

    Article  Google Scholar 

  17. Lorigo LM, Govindaraju V (2006) Offline arabic handwriting recognition: a survey. IEEE Trans Pattern Anal Mach Intell 28(5):712–724

    Article  Google Scholar 

  18. Srihari SN, Yang X, Ball GR (2007) Offline Chinese handwriting recognition: an assessment of current technology. Front Comput Sci China I(2):137–155

  19. Abuhaiba ISI, Mahmoud SA, Green RJ (1994) Recognition of handwritten cursive Arabic characters. IEEE Trans Pattern Anal Mach Intell 16:664–672

    Article  Google Scholar 

  20. Amin A, Al-Sadoun H, Fischer S (1996) Hand-printer arabic character recognition system using an artificial network. Pattern Recogn 29:663–675

    Article  Google Scholar 

  21. Makhoul J, Schwartz R, Lapre C, Bazzi I (1998) A script independent methodology for optical character recognition. Pattern Recogn 31:1285–1294

    Article  Google Scholar 

  22. Khorsheed MS, Clocksin WF (1999) Structural features of cursive arabic script. In: Proceedings of British Machine Vision Conference, pp 422–431

  23. Al-Shaher AA, Hancock ER (2003) Learning mixtures of point distribution models with the EM algorithm. Pattern Recogn 36:2805–2818

    Article  MATH  Google Scholar 

  24. Dehghani A, Shabani F, Nava P (2001) Offline recognition of isolated Persian handwritten characters using multiple hidden markov models. In: Proceedings of international conference on information technology: coding and computing, vol 20, pp 506–510

  25. Gillevic D, Suen CY (1998) HMM-KNN word recognition engine for bank cheque processing. In: Proceedings of International Conference on Pattern Recognition, Brisbane, Australia, August 1998, pp 1526–1529

  26. Kennr S, Anisimov V, Baret O, Gorski N, Price D, Simon IC (1997) The A2iA intercheque system: courtesy amount and legal amount recognition for French cheques. In: Impedovo S, Wang PSP, Bunke H (eds) Machine perception and artificial intelligence, vol 28. World Scientific, USA, pp 43–86

    Google Scholar 

  27. Kim G, Govindaraju V (1997) Bank cheque recognition using cross validation between legal and courtesy amounts. Int Conf Pattern Recogn Artif Intell 11(4):657–674

    Article  Google Scholar 

  28. Ko AH, Cavalin PR, Sabourin R, de Souza Britto A Jr (2009) Leave-one-out-training and leave-one-out-testing hidden markov models for a handwritten numeral recognizer: the implications of a single classifier and multiple classifications. IEEE Trans Pattern Anal Mach Intell 31(12):2168–2178

    Article  Google Scholar 

  29. Nunes CM, de S Britto Jr. A, Kaestner CAA, Sabourin R (2004) An optimized hill climbing algorithm for feature subset selection evaluation on handwritten character recognition. In: Proceedings of International Workshop on Frontiers in Handwriting Recognition, pp 365–370, 2004

  30. Giusti N, Masuli F, Sperduti A (2002) Theoretical and experimental analysis of a two stage system for classification. IEEE Trans Pattern Anal Mach Intell 24(7):893–904

    Article  Google Scholar 

  31. Cao J, Ahmadi M, Sridhar M (1995) Recognition of handwritten numerals with multiple features and multistage classifiers. Pattern Recogn 28(2):153–160

    Article  Google Scholar 

  32. Vamvakas G, Gatos B, Perantonis SJ (2010) Handwritten character recognition through two-stage foreground sub-sampling. Pattern Recogn 43:2807–2816

    Article  MATH  Google Scholar 

  33. Huang L, Liu C (2010) Handwritten Chinese character recognition method based on non-parametric dimensionality reduction. In: Proceedings of International Conference on Computer Design and Applications, pp VI-217–VI-220

  34. Tsukumo J, Tanaka H (1988) Classification of hand-printed Chinese characters using non linear normalization and correction methods. In: Proceedings of international conference on pattern recognition, Roma, Italy, pp 168–171

  35. Fu H-C, Xu Y–Y (1998) Multilinguistic handwritten character recognition by Bayesian decision based neural networks. IEEE Trans Signal Process 46(10):2781–2789

    Article  Google Scholar 

  36. Mao J, Mohiuddin KM (1997) Improving OCR performance using character degradation models and boosting algorithm. Pattern Recogn Lett 18:1415–1419

    Article  Google Scholar 

  37. Dong J-X, Krzyzack A, Suen C-Y (2005) Fast SVM training algorithm with decomposition on very large training sets. IEEE Trans Pattern Anal Mach Intell 27(4):603–618

    Article  Google Scholar 

  38. Liu C-L, Sako H, Fujisawa H (2003) Handwritten Chinese character recognition: alternatives to non linear normalization. In: Proceedings of international conference on document analysis and recognition, Edinburgh, Scotland, pp 524–528

  39. Liu C-L, Marukawa K (2005) Pseudo 2D shape normalization methods for handwritten Chinese character recognition. Pattern Recogn 38(12):2242–2255

    Article  Google Scholar 

  40. Liu C-L, Sako H, Fujisawa H (2002) Performance evaluation of pattern classifiers for handwritten character recognition. Int J Document Anal Recogn 4:191–204

    Article  Google Scholar 

  41. Kato N, Suzuki M, Omachi S, Aso H, Nemoto Y (1999) A handwritten character recognition system using directional element feature and symmetric Mahalanobis distance. IEEE Trans Pattern Anal Mach Intell 21(3):2781–2789

    Article  Google Scholar 

  42. Leung K-C, Leung CH (2009) Recognition of Chinese handwritten characters by combining regularization, Fisher’s discriminant and distorted sample generation. In: Proceedings of International Conference on Document Analysis and Recognition, pp 1026–1030, Barcelona

  43. Leung KC, Leung CH (2010) Recognition of handwritten Chinese characters by critical region analysis. Pattern Recogn 43:949–961

    Article  MATH  Google Scholar 

  44. Chinnuswamy P, Krishanmoorthy SG (1980) Recognition of hand-printer Tamil characters. Pattern Recogn 12(3):41–152

    Article  Google Scholar 

  45. Shanthi N, Duraiswamy K (2009) A Novel SVM-based handwritten Tamil character recognition. Pattern Anal Appl

  46. Sukhaswami MB, Seetharamulu P, Pujari AK (1995) Recognition of Telugu characters using neural networks. Int J Neural Syst 6(3):317–357

    Article  Google Scholar 

  47. Desai AA (2010) Gujarati handwritten numeral optical character recognition through neural network. Pattern Recogn 43:2582–2589

    Article  MATH  Google Scholar 

  48. Chaudhuri BB, Pal U (1997) Skew angle detection of digitized Indian script documents. IEEE Trans Pattern Anal Mach Intell 19(2):182–186

    Article  MathSciNet  Google Scholar 

  49. Rajasekararadhya SV, Ranjan PV (2009) Efficient zone based feature extraction algorithm for handwritten numeral recognition of popular south Indian scripts. J Tech Appl Inform Technol 7(1):1171–1180

    Google Scholar 

  50. Dutta A, Chaudhary S (1993) Bengali Alpha numeric character recognition using curvature features. Pattern Recogn 26(12):1757–1770

    Article  Google Scholar 

  51. Bhattacharya U, Das TK, Datta A, Parui SK, Chaudhuri BB (2002) A hybrid scheme for hand-printed numeral recognition based on a self organizing network and MLP classifiers. Int J Pattern Recogn Artif Intell 16(7):845–864

    Article  Google Scholar 

  52. Bhowmick TK, Bhattacharya U, Parui SK (2004) Recognition of Bangla handwritten characters using an MLP classifier based on stroke features. In: Proceedings of international conference on neural information processing, pp 814–819

  53. Hanmandlu M, Murthy OVR (2007) Fuzzy model based recognition of handwritten numerals. Pattern Recogn 40(6):1840–1854

    Article  MATH  Google Scholar 

  54. Banashree NP, Andhre D, Vasanta R, Satyanarayana PS (2007) OCR for script identification of Hindi (Devnagari) numerals using error diffusion Halftoning algorithm with neural classifier. Proc World Acad Sci Eng Technol 20:46–50

    Google Scholar 

  55. Lajish VL (2007) Adaptive neuro-fuzzy inference based pattern recognition studies on handwritten character images. Ph.D dissertation, University of Calicut, India

  56. Raju G, Moni BS (2009) Global and local elastic meshing for handwritten Malayalam character recognition. Int J Comput Inform Technol Eng 3(1):149–153

    Google Scholar 

  57. Moni BS, Raju G (2009) Meshing and normalized vector distance from centroid for handwritten Malayalam character recognition In: Procedings of ICSIP, pp 398–403

  58. Moni BS, Raju G (2009) Multiple MLP classifiers for handwritten Malayalam character recognition. In: Proceedings of ICMCM, pp 349–354

  59. Moni BS, Raju G (2010) Quadratic classifier for handwritten Malayalam character recognition. In: Proceedings of NCSC, pp 59–68

  60. Raju G, Moni BS (2009) Global elastic meshing for handwritten Malayalam character recognition. In: Proceedings of national conference on computer science and engineering, pp 10–14

  61. Chacko BP, Babu Anto P (2009) Discrete curve evolution based skeleton pruning for character recognition. In: Proceedings of IAPR, pp 402–405

  62. Chacko BP, Vimal Krishnan VR, Babu Anto P (2010) Character recognition using multiple back propagation algorithm. In: Proceedings of national conference on image processing, pp 209–212

  63. John R, Raju G, Guru DS (2007) 1D wavelet transform of projection profiles for isolated handwritten character recognition. In: Proceedings of ICCIMA, vol. 2, pp 481–485

  64. Wei XK, Li YH, Feng Y (2006) Comparative study of extreme learning machine and support vector machine, advances in neural networks, pp 1089–1095, 2006

  65. Mahmoud SA, Olatunji SO (2009) Automatic recognition of offline handwritten Arabic (Indian) numerals using support vector machine and extreme learning machine. Int J Imaging 2(A09):34–53

    Google Scholar 

  66. Li M, Wang C, Dai R (2008) Unconstrained handwritten character recognition based on WEDF and multilayer neural network. In: Proceedings of World Congress on Intelligent Control and Automation, pp 1143–1148

  67. Li H-N, He X-Y, Yi T-H (2009) Multi-component seismic response analysis of offshore platform by wavelet energy principle. Cost Eng 56:810–830

    Article  Google Scholar 

  68. Achuthan A, Rajeswari M, Ramachandram D, Aziz ME, Shuaib IL (2011) Wavelet energy-guided level set-based active contour: a segmentation method to segment highly similar regions. Comput Biol Med (in press)

  69. Favata J, Srikantan G, Srihari S (1994) Hand-printer character/digit recognition using a multiple feature/resolution philosophy. In: Proceedings of international workshop on frontiers of handwriting recognition, pp 57–66

  70. Park J, Govindaraju V, Srihari SN (2000) OCR in a hierarchical feature space. IEEE Trans Pattern Anal Mach Intell 2(4):400–407

    Article  Google Scholar 

  71. Raju G (2006) Recognition of unconstrained handwritten Malayalam characters using zero crossing of wavelet coefficients. In: Proceedings of international conference on Advanced Computing and Communications, pp 217–221

  72. Sasi S, Schwiebert L, Bedi JS (2007) Wavelet packet transform and neuro-fuzzy approach to handwritten character recognition

  73. Lee S-W, Kim C-H, Tang YY (1996) Multi-resolution recognition of unconstrained handwritten numerals with wavelet transform and multilayer cluster neural network. Pattern Recogn 29(12):1953–1961

    Article  Google Scholar 

  74. Correia SEN, Carvalho JM (2000) Optimizing the recognition rates of unconstrained handwritten numerals using biorthogonal spline wavelets, vol 2. ICPR, Barcelona, Spain, pp 2251

  75. Huang G-B, Babri HA (1998) Upper bounds on the number of hidden neurons in feed forward with arbitrary bounded non linear activations functions. IEEE Trans Neural Netw 9(1):224–229

    Article  Google Scholar 

  76. Liang N-Y, Huang G-B, Saratchandran P, Sundararajan N (2006) A fast and accurate online sequential learning algorithm for feed forward networks. IEEE Trans Neural Netw 17(6):1411–1423

    Article  Google Scholar 

  77. Suresh S, Saraswathi S, Sundararajan N (2010) Performance enhancement of extreme learning machine for multi-category sparse data classification problems. Eng Appl Artif Intell 23:1149–1157

    Article  Google Scholar 

  78. Suresh S, Venkatesh Babu R, Kim HJ (2009) No-reference image quality assessment using modified extreme learning machine classifier. Appl Soft Comput 9:541–552

    Article  Google Scholar 

  79. Rong HJ, Ong YS, Tan AW, Zhu Z (2008) A fast pruned extreme learning machine for classification problem. Neurocomputing 72:359–366

    Article  Google Scholar 

  80. Miche Y, Sorjamma A, Bas P, Simula O, Jutten C, Lendasse A (2010) OP-ELM: optimally pruned extreme learning machine. IEEE Trans Neural Netw 21(1):158–162

    Article  Google Scholar 

  81. Lan Y, Soh YC, Huang GB (2010) Constructive hidden nodes selection of extreme learning machine for regression. Neurocomputing 73(16–18):3191–3199

    Article  Google Scholar 

  82. Lan Y, Soh YC, Huang GB (2010) Two stage extreme learning machine for regression. Neurocomputing 73:3028–3038

    Article  Google Scholar 

  83. Huang G-B, Chen L (2007) Convex incremental extreme learning machine. Neurocomputing 70:3056–3062

    Article  Google Scholar 

  84. Barron AR (1993) Universal approximation bounds for superstitions of a sigmoidal function. IEEE Trans Inf Theory 39(3):930–945

    Article  MathSciNet  MATH  Google Scholar 

  85. Huang G-B, Chen L (2008) Enhanced random search based incremental extreme learning machine. Neurocomputing 71:3460–3468

    Article  Google Scholar 

  86. Feng G, Huang G-B, Lin Q, Gay R (2009) Error minimized extreme learning machine with growth of hidden nodes and incremental learning. IEEE Trans Neural Netw 20(8):1352–1357

    Article  Google Scholar 

  87. Moni BS, Raju G (2011) Modified quadratic classifier and normalized vector distance for handwritten malayalam character recognition. In: Proceedings of international conference on emerging trends in mathematics and computer applications, pp 356–360, December 2011

  88. Moni BS, Raju G (2011) Modified quadratic classifier for handwritten Malayalam character recognition using run length count. In: Proceedings of international conference on emerging trends in electrical and computer technology

  89. Moni BS, Raju G (2011) Modified quadratic classifer for handwritten character recognition using gradient features. In: Proceedings of Natural Conference on Indian Language Computing

  90. Chacko BP, Babu Anto P (2010) Pre and post processing approaches in edge detection for character recognition. In: Proceedings of international conference on frontiers in handwriting recognition, pp 676–681

Download references

Acknowledgments

The authors are grateful to reviewers who have helped us to prepare this paper in the present form. Also, the authors thank University Grants Commission and Kerala State Council for Science, Technology and Environment for providing fellowship to Binu P. Chacko and Vimal Krishnan V R respectively, to carry out this research work.

Author information

Authors and Affiliations

  1. Department of Information Technology, Kannur University, Kannur, India

    Binu P. Chacko, V. R. Vimal Krishnan, G. Raju & P. Babu Anto

Authors
  1. Binu P. Chacko
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. V. R. Vimal Krishnan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. G. Raju
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. P. Babu Anto
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Binu P. Chacko.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Chacko, B.P., Vimal Krishnan, V.R., Raju, G. et al. Handwritten character recognition using wavelet energy and extreme learning machine. Int. J. Mach. Learn. & Cyber. 3, 149–161 (2012). https://doi.org/10.1007/s13042-011-0049-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-011-0049-5

Keywords

Search

Navigation