Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Analysis and comparison of machine learning classifiers and deep neural networks techniques for recognition of Farsi handwritten digits

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Handwriting recognition remains a challenge in the machine vision field, especially in optical character recognition (OCR). The OCR has various applications such as the detection of handwritten Farsi digits and the diagnosis of biomedical science. In expanding and improving quality of the subject, this research focus on the recognition of Farsi Handwriting Digits and illustration applications in biomedical science. The detection of handwritten Farsi digits is being widely used in most contexts involving the collection of generic digital numerical information, such as reading checks or digits of postcodes. Selecting an appropriate classifier has become an issue highlighted in the recognition of handwritten digits. The paper aims at identifying handwritten Farsi digits written with different handwritten styles. Digits are classified using several traditional methods, including K-nearest neighbor, artificial neural network (ANN), and support vector machine (SVM) classifiers. New features of digits, namely, geometric and correlation-based features, have demonstrated to achieve better recognition performance. A noble class of methods, known as deep neural networks (DNNs), is also used to identify handwritten digits through machine vision. Here, two types of introduce its expansion form, a convolutional neural network (CNN) and an auto-encoder, are implemented. Moreover, by using a new combination of CNN layers one can obtain improved results in classifying Farsi digits. The performances of the DNN-based and traditional classifiers are compared to investigate the improvements in accuracy and calculation time. The SVM shows the best results among the traditional classifiers, whereas the CNN achieves the best results among the investigated techniques. The ANN offers better execution time than the SVM, but its accuracy is lower. The best accuracy among the traditional classifiers based on all investigated features is 99.3% accuracy obtained by the SVM, and the CNN achieves the best overall accuracy of 99.45%.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Akhtar MS, Qureshi HA, Alquhayz H (2019) High-quality wavelets features extraction for handwritten arabic numerals recognition. Int J Adv Sci Eng Inf Technol 9:700–710

    Article  Google Scholar 

  2. Alaei A, Pal U, Nagabhushan P (2009) Using modified contour features and SVM based classifier for the recognition of Persian/Arabic handwritten numerals. In: 2009 Seventh International Conference on Advances in Pattern Recognition, IEEE, pp 391–394

  3. Alaei A, Nagabhushan P, Pal U (2009) Fine classification of unconstrained handwritten Persian/Arabic numerals by removing confusion amongst similar classes. In: 2009 10th International Conference on Document Analysis and Recognition, IEEE, pp 601–605

  4. Alghazo JM, Latif G, Alzubaidi L, Elhassan A (2019) Multi-language handwritten digits recognition based on novel structural features. J Imaging Sci Technol 63(2):20502-1

    Article  Google Scholar 

  5. Arani SAAA, Kabir E, Ebrahimpour R (2019) Handwritten Farsi word recognition using NN-based fusion of HMM classifiers with different types of features. Int J Image Graph 19(01):195–218

    Article  Google Scholar 

  6. Ashiquzzaman A, Tushar AK (2017) Handwritten Arabic numeral recognition using deep learning neural networks. In: 2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR). IEEE, pp 1–4

  7. Ayyadevara SA, Teja S, Rajesh Kumar M (2018). Handwritten character recognition using unique feature extraction technique. In: 2018 3rd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology (RTEICT), Bangalore, India, pp 1239–1243

  8. Bhatia N (2010) Survey of nearest neighbor techniques. arXiv preprint arXiv:1007.0085

  9. Boukharouba A, Bennia A (2017) Novel feature extraction technique for the recognition of handwritten digits. Appl Comput Inform 13(1):19–26

    Article  Google Scholar 

  10. Cheok MJ, Omar Z, Jaward MH (2019) A review of hand gesture and sign language recognition techniques. Int J Mach Learn Cybernet 10(1):131–153

    Article  Google Scholar 

  11. Dehghanian A, Ghods V.(2018) Farsi handwriting digit recognition based on convolutional neural networks. In: 2018 6th International Symposium on Computational and Business Intelligence (ISCBI), pp 65–68

  12. Deng L, Yu D (2014) Deep learning: methods and applications. Found Trends Signal Process 7(3–4):197–387

    Article  MathSciNet  Google Scholar 

  13. Fausett L (1994) Fundamentals of neural networks: architectures, algorithms, and applications. Prentice-Hall Inc, London

    MATH  Google Scholar 

  14. Guo K, Guo W, Chen Y, Qiu Q, Zhang Q (2015) Community discovery by propagating local and global information based on the MapReduce model. Inf Sci 323:73–93

    Article  MathSciNet  Google Scholar 

  15. Guo WZ, Chen JY, Chen GL, Zheng HF (2015) Trust dynamic task allocation algorithm with Nash equilibrium for heterogeneous wireless sensor network. Secur Commun Netw 8(10):1865–1877

    Article  Google Scholar 

  16. Hamidi M, Borji A (2010) Invariance analysis of modified C2 features: case study—handwritten digit recognition. Mach Vis Appl 21(6):969–979

    Article  Google Scholar 

  17. Huang X, Guo W, Liu G, Chen G (2016) FH-OAOS: a fast four-step heuristic for obstacle-avoiding octilinear Steiner tree construction. ACM Trans Des Autom Electron Syst 21(3):1–31

    Google Scholar 

  18. Huang X, Guo W, Liu G, Chen G (2017) MLXR: multi-layer obstacle-avoiding X-architecture Steiner tree construction for VLSI routing. Sci China Inf Sci 60(1):19102

    Article  Google Scholar 

  19. Islam A, Fuad R, AKM S (2019) Sankhya: an unbiased benchmark for bangla handwritten digits recognition. In: 2019 IEEE International Conference on Big Data (Big data), pp 78–89

  20. Kalyampudi PL, Rao PS, Swapna D (2019) An efficient digit recognition system with an improved preprocessing technique. In: International conference on intelligent computing and communication technologies. Springer, Singapore, pp 312–321

  21. Karimi H, Esfahanimehr A, Mosleh M, Salehpour S, Medhati O (2015) Persian handwritten digit recognition using ensemble classifiers. Procedia Comput Sci 73:416–425

    Article  Google Scholar 

  22. Khosravi H, Kabir E (2007) Introducing a very large dataset of handwritten Farsi digits and a study on their varieties. Pattern Recognit Lett 28(10):1133–1141

    Article  Google Scholar 

  23. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980

  24. Krishnamurthi R, Patan R, Gandomi AH (2019) Assistive pointer device for limb impaired people: a novel frontier point method for hand movement recognition. Future Gener Comput Syst 98:650–659

    Article  Google Scholar 

  25. Liu G, Guo W, Niu Y, Chen G, Huang X (2015) A PSO-based timing-driven Octilinear Steiner tree algorithm for VLSI routing considering bend reduction. Soft Comput 19(5):1153–1169

    Article  Google Scholar 

  26. Liu G, Guo W, Li R, Niu Y, Chen G (2015) XGRouter: high-quality global router in X-architecture with particle swarm optimization. Front Comput Sci 9(4):576–594

    Article  Google Scholar 

  27. Liu G, Chen Z, Zhuang Z, Guo W, Chen G (2020) A unified algorithm based on HTS and self-adapting PSO for the construction of octagonal and rectilinear SMT. Soft Comput 24(6):3943–3961

    Article  Google Scholar 

  28. Mohammadpoor M, Mehdizadeh A, Noghabi HA (2018) A novel method for persian handwritten digit recognition using support vector machine. Majlesi J Electr Eng 12(3):63–67

    Google Scholar 

  29. Mowlaei A, Faez K, Haghighat AT (2002) Feature extraction with wavelet transform for recognition of isolated handwritten Farsi/Arabic characters and numerals. In: 2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No. 02TH8628). IEEE, vol 2, pp 923–926

  30. Narasimha RS, Parag S (2018) Review of feature extraction techniques for character recognition. IETE J Res 64(2):280–295

    Article  Google Scholar 

  31. Neri C, Vergara V, Cruz O, Nandayapa M Azuela J (2020) A convolutional neural network for handwritten digit recognition. Int J Comb Optim Prob Inform 11(1): 97–105

    Google Scholar 

  32. Noaparast K, Broumandnia A (2009) Persian handwritten word recognition using Zernike and Fourier–Mellin moments. In: 5th International Conference Sciences of Electronic Technologies of Information and Telecommunications

  33. Peres A, Vieira SM, Pinto JR (2018) Hybrid neural models for automatic handwritten digits recognition. In: 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, pp 1–8

  34. Saini H, Sahni V (2017) Region growing segmentation using de-noising algorithm for medical ultrasound images. In: 2017 3rd International Conference on Computational Intelligence and Communication Technology (CICT). IEEE, pp 1–5

  35. Salimi H, Giveki D (2013) Farsi/Arabic handwritten digit recognition based on ensemble of SVD classifiers and reliable multi-phase PSO combination rule. Int J Doc Anal Recognit 16(4):371–386

    Article  Google Scholar 

  36. Sarigül M, Avci M (2018) Performance comparison of different momentum techniques on deep reinforcement learning. J Inf Telecommun 2(2):205–216

    Google Scholar 

  37. Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117

    Article  Google Scholar 

  38. Soltanzadeh H, Rahmati M (2004) Recognition of Persian handwritten digits using image profiles of multiple orientations. Pattern Recognit Lett 25(14):1569–1576

    Article  Google Scholar 

  39. Sufian A, Ghosh A, Naskar A, Sultana F (2019) Bdnet: bengali handwritten numeral digit recognition based on densely connected convolutional neural networks. arXiv preprint arXiv:1906.03786

  40. Uysal AK, Gunal S (2014) The impact of preprocessing on text classification. Inf Process Manag 50(1):104–112

    Article  Google Scholar 

  41. Vamvakas G, Gatos B, Perantonis SJ (2010) Handwritten character recognition through two-stage foreground sub-sampling. Pattern Recognit 43(8):2807–2816

    Article  Google Scholar 

  42. Wang J, Zhang XM, Lin Y, Ge X, Han QL (2018) Event-triggered dissipative control for networked stochastic systems under non-uniform sampling. Inf Sci 447:216–228

    Article  Google Scholar 

  43. Xia Y, Leung H (2014) Performance analysis of statistical optimal data fusion algorithms. Inf Sci 277:808–824

    Article  MathSciNet  Google Scholar 

  44. Xia Y, Wang J (2015) Low-dimensional recurrent neural network-based Kalman filter for speech enhancement. Neural Netw 67:131–139

    Article  Google Scholar 

  45. Xu Y, Guo R, Wang L (2013) A twin multi-class classification support vector machine. Cognitive computation 5(4):580–588

    Article  Google Scholar 

  46. Yang LH, Wang YM, Su Q, Fu YG, Chin KS (2016) Multi-attribute search framework for optimizing extended belief rule-based systems. Inf Sci 370:159–183

    Article  Google Scholar 

  47. Yang Y (2014) Broadcast encryption based non-interactive key distribution in MANETs. J Comput Syst Sci 80(3):533–545

    Article  Google Scholar 

  48. Zhang P, Bui TD, Suen CY (2007) A novel cascade ensemble classifier system with a high recognition performance on handwritten digits. Pattern Recognit 40(12):3415–3429

    Article  Google Scholar 

  49. Zhang S, Xia Y, Wang J (2015) A complex-valued projection neural network for constrained optimization of real functions in complex variables. IEEE Trans Neural Netw Learn Syst 26(12):3227–3238

    Article  MathSciNet  Google Scholar 

  50. Zhang S, Xia Y, Zheng W (2015) A complex-valued neural dynamical optimization approach and its stability analysis. Neural Netw 61:59–67

    Article  Google Scholar 

  51. Zhong S, Chen T, He F, Niu Y (2014) Fast Gaussian kernel learning for classification tasks based on specially structured global optimization. Neural Netw 57:51–62

    Article  Google Scholar 

  52. Zhu W, Lin G, Ali MM (2013) Max-k-cut by the discrete dynamic convexized method. INFORMS J Comput 25(1):27–40

    Article  MathSciNet  Google Scholar 

  53. Zou J, Dong L, Wu W (2018) New algorithms for the unbalanced generalised birthday problem. IET Inf Secur 12(6):527–533

    Article  Google Scholar 

Download references

Acknowledgements

The authors extend their appreciation to the Deanship of Scientific Research at King Saud University for funding this work through Research Group No. RG-1441-331.

Author information

Authors and Affiliations

  1. Informatics School of Xiamen University, Xiamen, 361005, Fujian, People’s Republic of China

    Y. A. Nanehkaran, Defu Zhang & Junde Chen

  2. Department of Electrical and Computer Engineering, Seraj Institute of Higher Education, Tabriz, Iran

    S. Salimi

  3. School of Computer Engineering, Nanjing Institute of Technology, Nanjing, Jiangsu, People’s Republic of China

    Yuan Tian

  4. Department of Computer Science, King Saud University, Riyadh, Kingdom of Saudi Arabia

    Najla Al-Nabhan

Authors
  1. Y. A. Nanehkaran
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Defu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. S. Salimi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Junde Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yuan Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Najla Al-Nabhan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Defu Zhang.

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

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Nanehkaran, Y.A., Zhang, D., Salimi, S. et al. Analysis and comparison of machine learning classifiers and deep neural networks techniques for recognition of Farsi handwritten digits. J Supercomput 77, 3193–3222 (2021). https://doi.org/10.1007/s11227-020-03388-7

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-020-03388-7

Keywords

Search

Navigation