An empirical evaluation of extreme learning machine: application to handwritten character recognition


Extreme learning machine (ELM), a randomized learning paradigm for single hidden layer feed-forward network, has gained significant attention for solving problems in diverse domains due to its faster learning ability. The output weights in ELM are determined by an analytic procedure, while the input weights and biases are randomly generated and fixed during the training phase. The learning performance of ELM is highly sensitive to many factors such as the number of nodes in the hidden layer, the initialization of input weight and the type of activation functions in the hidden layer. Although various works on ELM have been proposed in the last decade, the effect of the all these influencing factors on classification performance has not been fully investigated yet. In this paper, we test the performance of ELM with different configurations through an empirical evaluation on three standard handwritten character datasets, namely, MNIST, ISI-Kolkata Bangla numeral, ISI-Kolkata Odia numeral and a newly developed NIT-RKL Bangla numeral dataset. Finally, we derive some best ELM figurations which can serve as general guidelines to design ELM based classifiers.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3


  1. 1.


  1. 1.

    Basu S, Das N, Sarkar R, Kundu M, Nasipuri M, Basu DK (2010) A novel framework for automatic sorting of postal documents with multi-script address blocks. Pattern Recogn 43(10):3507–3521

    Article  MATH  Google Scholar 

  2. 2.

    Bhalerao M, Bonde S, Nandedkar A, Pilawan S (2018) Combined classifier approach for offline handwritten Devanagari character recognition using multiple features. In: Computational vision and bio inspired computing. Springer, pp 45–54

  3. 3.

    Bhattacharya U, Chaudhuri B (2005) Databases for research on recognition of handwritten characters of Indian scripts. In: Eighth International conference on document analysis and recognition, 2005. Proceedings. IEEE, pp 789–793

  4. 4.

    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 

  5. 5.

    Bhowmik TK, Parui SK, Bhattacharya U, Shaw B (2006) An HMM based recognition scheme for handwritten Oriya numerals. In: International conference on information technology IEEE, pp 105–110.

  6. 6.

    Broomhead DS, Lowe D (1988) Radial basis functions, multi-variable functional interpolation and adaptive networks. Tech. rep, Royal Signals and Radar Establishment Malvern (United Kingdom)

  7. 7.

    Cecotti H (2016) Deep random vector functional link network for handwritten character recognition. In: 2016 International joint conference on neural networks (IJCNN). IEEE, pp 3628–3633

  8. 8.

    Cireşan DC, Meier U, Gambardella LM, Schmidhuber J (2010) Deep, big, simple neural nets for handwritten digit recognition. Neural Comput 22(12):3207–3220

    Article  Google Scholar 

  9. 9.

    Cui D, Huang GB, Liu T (2018) ELM based smile detection using distance vector. Pattern Recogn 79:356–369

    Article  Google Scholar 

  10. 10.

    Dash KS, Puhan N, Panda G (2014) A hybrid feature and discriminant classifier for high accuracy handwritten Odia numeral recognition. In: IEEE Region 10 symposium. IEEE, pp 531–535

  11. 11.

    Dash KS, Puhan N, Panda G (2014) Non-redundant stockwell transform based feature extraction for handwritten digit recognition. In: International conference on signal processing and communications. IEEE, pp 1–4

  12. 12.

    Dash KS, Puhan N, Panda G (2015) On extraction of features for handwritten Odia numeral recognition in transformed domain. In: Eighth International conference on advances in pattern recognition. IEEE, pp 1–6

  13. 13.

    Eshtay M, Faris H, Obeid N (2018) Improving extreme learning machine by competitive swarm optimization and its application for medical diagnosis problems. Expert Systems with Applications

  14. 14.

    Ghosh D, Dube T, Shivaprasad A (2010) Script recognition—a review. IEEE Trans Pattern Anal Mach Intell 32(12):2142–2161

    Article  Google Scholar 

  15. 15.

    Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp 249–256

  16. 16.

    He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  17. 17.

    Huang GB, Siew CK (2004) Extreme learning machine: RBF network case. In: Control, automation, robotics and vision conference, vol 2. IEEE, pp 1029–1036

  18. 18.

    Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1–3):489–501

    Article  Google Scholar 

  19. 19.

    Huang GB, Chen L, Siew CK, et al. (2006) Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw 17(4):879–892

    Article  Google Scholar 

  20. 20.

    Huang GB, Wang D, Lan Y (2011) Extreme learning machines: a survey. Int J Mach Learn Cybern 2(2):107–122

    Article  Google Scholar 

  21. 21.

    Huang GB, Zhou H, Ding X, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part B (Cybern) 42(2):513–529

    Article  Google Scholar 

  22. 22.

    Kasun LLC, Yang Y, Huang GB, Zhang Z (2016) Dimension reduction with extreme learning machine. IEEE Trans Image Process 25(8):3906–3918

    MathSciNet  Article  MATH  Google Scholar 

  23. 23.

    Kégl B, Busa-Fekete R (2009) Boosting products of base classifiers. In: Proceedings of the 26th annual international conference on machine learning. ACM, pp 497–504

  24. 24.

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

    Article  Google Scholar 

  25. 25.

    Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324

    Article  Google Scholar 

  26. 26.

    Liang NY, Huang GB, Saratchandran P, Sundararajan N (2006) A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Trans Neural Netw 17(6):1411–1423

    Article  Google Scholar 

  27. 27.

    Liu CL, Suen CY (2009) A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters. Pattern Recogn 42(12):3287–3295

    Article  MATH  Google Scholar 

  28. 28.

    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 

  29. 29.

    Liu T, Lekamalage CKL, Huang GB, Lin Z (2018) Extreme learning machine for joint embedding and clustering. Neurocomputing 277:78–88

    Article  Google Scholar 

  30. 30.

    Mahto MK, Kumari A, Panigrahi S (2011) A system for Oriya handwritten numeral recognition for Indian postal automation. Int J Appl Sci Technol Res Excell 1 (1):17–23

    Google Scholar 

  31. 31.

    Mishra TK, Majhi B, Panda S (2013) A comparative analysis of image transformations for handwritten Odia numeral recognition. In: International conference on advances in computing, communications and informatics. IEEE, pp 790–793

  32. 32.

    Mishra TK, Majhi B, Sa PK, Panda S (2014) Model based Odia numeral recognition using fuzzy aggregated features. Front Comput Sci 8(6):916–922

    MathSciNet  Article  Google Scholar 

  33. 33.

    Mohammed AA, Minhas R, Wu QJ, Sid-Ahmed MA (2011) Human face recognition based on multidimensional pca and extreme learning machine. Pattern Recogn 44(10-11):2588–2597

    Article  MATH  Google Scholar 

  34. 34.

    Mohapatra RK, Majhi B, Jena SK (2015) Classification performance analysis of mnist dataset utilizing a multi-resolution technique. In: International conference on computing, communication and security (ICCCS), 2015. IEEE, pp 1–5

  35. 35.

    Mori S, Suen CY, Yamamoto K (1995) Historical review of OCR research and development. In: Document image analysis. IEEE Computer Society Press, pp 244–273

  36. 36.

    Nayak DR, Dash R, Majhi B (2017) Development of pathological brain detection system using jaya optimized improved extreme learning machine and orthogonal ripplet-ii transform. Multimed Tools Appl, 1–29

  37. 37.

    Nayak DR, Dash R, Majhi B (2018) Discrete ripplet-ii transform and modified PSO based improved evolutionary extreme learning machine for pathological brain detection. Neurocomputing 282:232–247

    Article  Google Scholar 

  38. 38.

    Pan C, Park DS, Yang Y, Yoo HM (2012) Leukocyte image segmentation by visual attention and extreme learning machine. Neural Comput and Applic 21 (6):1217–1227

    Article  Google Scholar 

  39. 39.

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

    Article  Google Scholar 

  40. 40.

    Sarangi PK, Ahmed P, Ravulakollu KK (2014) Naïve bayes classifier with lu factorization for recognition of handwritten Odia numerals. Indian J Sci Technol 7 (1):35–38

    Google Scholar 

  41. 41.

    Sethy A, Patra PK, Nayak DR (2018) Gray-level co-occurrence matrix and random forest based off-line Odia handwritten character recognition. Recent Patents on Engineering

  42. 42.

    Sethy A, Patra PK, Nayak DR (2018) Off-line handwritten Odia character recognition using DWT and PCA. In: Progress in advanced computing and intelligent engineering. Springer, pp 187–195

  43. 43.

    Song Y, He B, Zhao Y, Li G, Sha Q, Shen Y, Yan T, Nian R, Lendasse A (2018) Segmentation of sidescan sonar imagery using markov random fields and extreme learning machine. IEEE Journal of Oceanic Engineering

  44. 44.

    Tang B, Liu X, Lei J, Song M, Tao D, Sun S, Dong F (2016) Deepchart: combining deep convolutional networks and deep belief networks in chart classification. Signal Process 124:156–161

    Article  Google Scholar 

  45. 45.

    Tao D, Lin X, Jin L, Li X (2016) Principal component 2-D long short-term memory for font recognition on single Chinese characters. IEEE Trans Cybern 46 (3):756–765

    Article  Google Scholar 

  46. 46.

    Tao D, Guo Y, Li Y, Gao X (2018) Tensor rank preserving discriminant analysis for facial recognition. IEEE Trans Image Process 27(1):325–334

    MathSciNet  Article  MATH  Google Scholar 

  47. 47.

    Wang D (2016) Editorial: randomized algorithms for training neural networks. Inform Sci 364–365:126–128

    Article  Google Scholar 

  48. 48.

    Wen Y, He L (2012) A classifier for Bangla handwritten numeral recognition. Expert Syst Appl 39(1):948–953

    Article  Google Scholar 

  49. 49.

    Wen Y, Lu Y, Shi P (2007) Handwritten Bangla numeral recognition system and its application to postal automation. Pattern Recogn 40(1):99–107

    Article  MATH  Google Scholar 

  50. 50.

    Wen X, Liu H, Yan G, Sun F (2018) Weakly paired multimodal fusion using multilayer extreme learning machine. Soft Comput 22(11):3533–3544

    Article  MATH  Google Scholar 

  51. 51.

    Weng Q, Mao Z, Lin J, Liao X (2018) Land-use scene classification based on a CNN using a constrained extreme learning machine. Int J Remote Sens, 1–19

  52. 52.

    Xie W, Li Y, Ma Y (2016) Breast mass classification in digital mammography based on extreme learning machine. Neurocomputing 173:930–941

    Article  Google Scholar 

  53. 53.

    Xu Y, Shu Y (2006) Evolutionary extreme learning machine–based on particle swarm optimization. In: International symposium on neural networks. Springer, pp 644–652

  54. 54.

    Zeng N, Zhang H, Liu W, Liang J, Alsaadi FE (2017) A switching delayed PSO optimized extreme learning machine for short-term load forecasting. Neurocomputing 240:175–182

    Article  Google Scholar 

  55. 55.

    Zhang YD, Zhao G, Sun J, Wu X, Wang ZH, Liu HM, Govindaraj VV, Zhan T, Li J (2017) Smart pathological brain detection by synthetic minority oversampling technique, extreme learning machine, and jaya algorithm. Multimed Tools Appl, 1–20

  56. 56.

    Zou W, Yao F, Zhang B, Guan Z (2018) Back propagation convex extreme learning machine. In: Proceedings of ELM-2016. Springer, pp 259–272

Download references

Author information



Corresponding author

Correspondence to Deepak Ranjan Nayak.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Das, D., Nayak, D.R., Dash, R. et al. An empirical evaluation of extreme learning machine: application to handwritten character recognition. Multimed Tools Appl 78, 19495–19523 (2019).

Download citation


  • Extreme learning machine
  • Weight initialization
  • Activation function
  • Character recognition