Skip to main content
SpringerLink
Log in

Handwritten Arabic numerals recognition using convolutional neural network

  • Original Research
  • Published:
Journal of Ambient Intelligence and Humanized Computing Aims and scope Submit manuscript

Abstract

Numeral recognition is an important preliminary step for optical character recognition, document understanding and others. Deep learning based numeral recognition models have achieved huge popularity among the researchers around the world since last few years. Several convolutional neural network (CNN) based architectures have been proposed and many of those have achieved state-of-the-art results in numeral recognition. In this paper, we have explored CNN based architectures for handwritten Arabic numeral recognition. We have also developed a handwritten Arabic numerals dataset using various morphological operations on an existing dataset thus increasing the size of the dataset from 3000 to 72,000 images. A modification of previously proposed CNN architecture has given us an accuracy of 98.91% and our proposed architecture has produced 99.76%, which is comparable to state-of-the-art results found in the domain of handwritten Arabic numeral recognition.

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
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  • Abdleazeem S, El-Sherif E (2008) Arabic handwritten digit recognition. Int J Doc Anal Recogn 11(3):127–141. https://doi.org/10.1007/s10032-008-0073-5

    Article  Google Scholar 

  • Aggarwal A, Renudhir RR (2012) Recognition of Devanagari handwritten numerals using gradient features and SVM. Int J Comput Appl 48(8):39–44. https://doi.org/10.5120/7371-0151

    Article  Google Scholar 

  • Ahmad A, Maen H (2008) Recognition of on-line handwritten Arabic digits using structural features and transition network. Informatica 32(3):275–281

    MATH  Google Scholar 

  • Akhand MAH, Ahmed M, Rahman MH, Islam MM (2018) Convolutional neural network training incorporating rotation-based generated patterns and handwritten numeral recognition of major indian scripts. IETE J Res 64(2):176–194. https://doi.org/10.1080/03772063.2017.1351322

    Article  Google Scholar 

  • Alaei A, Pal U, Nagabhushan P (2009) Using modified contour features and SVM based classifier for the recognition of Persian/Arabic handwritten numerals. In: Proceedings of the 7th international conference on advances in pattern recognition. Kolkata, India: IEEE, pp 391–394. https://doi.org/10.1109/ICAPR.2009.14

  • Alani A (2017) Arabic handwritten digit recognition based on restricted Boltzmann machine and convolutional neural networks. Information 8(4):142. https://doi.org/10.3390/info8040142

    Article  Google Scholar 

  • Alom MZ, Sidike P, Taha TM, Asari VK (2017) Handwritten Bangla digit recognition using deep learning. In arXiv preprint arXiv:1705.02680

  • Ashiquzzaman A, Tushar AK (2017) Handwritten Arabic numeral recognition using deep learning neural networks. In: Proceedings of the IEEE international conference on imaging, vision pattern recognition. Dhaka, Bangladesh: IEEE, pp 1–4. https://doi.org/10.1109/ICIVPR.2017.7890866

  • Ashiquzzaman A, Tushar AK, Rahman A, Mohsin F (2019) An efficient recognition method for handwritten arabic numerals using CNN with data augmentation and dropout. In: Data management, analytics and innovation. Springer, Singapore, pp 299–309. https://doi.org/10.1007/978-981-13-1402-5_23

  • Basu S, Das N, Sarkar R, Kundu M, Nasipuri M, Basu DK (2009) Recognition of numeric postal codes from multi-script postal address blocks. In: Proceedings of the 3rd international conference on pattern recognition and machine intelligence. New Delhi, India: Springer, pp 381–386. https://doi.org/10.1007/978-3-642-11164-8_62

  • 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. https://doi.org/10.1109/TPAMI.2008.88

    Article  Google Scholar 

  • Bhowmik TK, Parui SK, Bhattacharya U, Shaw B (2006) An HMM based recognition scheme for handwritten Oriya numerals. In: Proceedings of the 9th international conference on information technology. Bhubaneswar, India: IEEE, pp 105–110. https://doi.org/10.1109/ICIT.2006.29

  • Chaurasia S, Agarwal S (2018) Recognition of handwritten numerals of various indian regional languages using deep learning. In: Proceedings of the 5th international conference on electrical, electronics and computer engineering. Gorakhpur, India: IEEE, pp 1–6. https://doi.org/10.1109/UPCON.2018.8596818

  • Das N, Mollah AF, Saha S, Haque SS (2006) Handwritten arabic numeral recognition using a multi-layer perceptron. In: Proceedings of national conference on recent trends in information systems. Kolkata, India, pp 200–203

  • Das N, Reddy JM, Sarkar R, Basu S, Kundu M, Nasipuri M, Basu DK (2012) A statistical–topological feature combination for recognition of handwritten numerals. Appl Soft Comput 12(8):2486–2495. https://doi.org/10.1016/j.asoc.2012.03.039

    Article  Google Scholar 

  • Dash KS, Puhan NB, Panda G (2015) Synthetic handwritten Odia numeral database: From shallow hundreds to comprehensive thousands. In: Proceedings of the 5th national conference on computer vision, pattern recognition, image processing and graphics. Patna, India: IEEE, pp 1–4. https://doi.org/10.1109/NCVPRIPG.2015.7490025

  • Dash KS, Puhan NB, Panda G (2018) Unconstrained handwritten digit recognition using perceptual shape primitives. Pattern Anal Appl 21(2):413–436. https://doi.org/10.1007/s10044-016-0586-3

    Article  MathSciNet  Google Scholar 

  • De Campos TE, Babu BR, Varma M (2009) Character recognition in natural images. In: Proceedings of the 4th international conference on computer vision theory and applications. Lisboa, Portugal, pp 273–280. https://doi.org/10.5220/0001770102730280

  • Devanagari Character Dataset (2012) Kaggle dataset [Online]. https://www.kaggle.com/ashokpant/devanagari-character-dataset/data. Accessed 27 May 2019

  • Diem, M, Fiel S, Kleber F, Sablatnig R, Saavedra JM, Contreras D, Barrios JM, Oliveira LS (2014) competition on handwritten digit string recognition in challenging datasets (HDSRC 2014). In: Proceedings of the 14th international conference on frontiers in handwriting recognition. Heraklion, Greece: IEEE, pp 779–784. https://doi.org/10.1109/ICFHR.2014.136

  • Djeddi C, Gattal A, Souici-Meslati L, Siddiqi I, Chibani Y, El Abed H (2014) LAMIS-MSHD a multi-script offline handwriting database. In: Proceedings of the 14th international conference on frontiers in handwriting recognition. Heraklion, Greece: IEEE, pp 93–97. https://doi.org/10.1109/ICFHR.2014.23

  • El-Sawy A, Hazem EB, Loey M (2016) CNN for handwritten Arabic digits recognition based on LeNet-5. In: Proceedings of international conference on advanced intelligent systems and informatics. Springer, pp 566–575. https://doi.org/10.1007/978-3-319-48308-5_54

  • Farhat W, Sghaier S, Faiedh H, Souani C (2019) Design of efficient embedded system for road sign recognition. J Ambient Intell Hum Comput 10(2):491–507. https://doi.org/10.1007/s12652-017-0673-3

    Article  Google Scholar 

  • Ghosh S, Das N, Kundu M, Nasipuri M (2016) Handwritten oriya digit recognition using maximum common subgraph based similarity measures. In: Proceedings of the 3rd international conference India. New Delhi, India: Springer, pp 165–173. https://doi.org/10.1007/978-81-322-2757-1_18

  • Harifi A, Aghagolzadeh A (2007) A new pattern for handwritten Persian/Arabic digit recognition. Int J Comput Electr Automat Control Inf Eng 1(3):798–801. https://doi.org/10.5281/zenodo.1083765

    Article  Google Scholar 

  • He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904–1916. https://doi.org/10.1109/TPAMI.2015.2389824

    Article  Google Scholar 

  • Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of international conference on computer vision and pattern recognition. USA, IEEE, pp 4700–4708. https://doi.org/10.1109/cvpr.2017.243

  • Khosravi H, Kabir E (2007) Introducing a very large dataset of handwritten Farsi digits and a study on their varieties. Pattern Recogn Lett 28(10):1133–1141. https://doi.org/10.1016/j.patrec.2006.12.022

    Article  Google Scholar 

  • Krizhevsky A, Sutskever V, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Proceedings of 25th international conference on neural information processing systems, December, 2012 ACM, pp 1097–1105

  • Kusetogullari H, Yavariabdi A, Cheddad A, Grahn H, Hall J (2019) ARDIS a Swedish historical handwritten digit dataset. Neural Comput Appl. https://doi.org/10.1007/s00521-019-04163-3

    Article  Google Scholar 

  • Lawal IA, Abdel-Aal RE, Mahmoud SA (2010) Recognition of handwritten Arabic (Indian) numerals using Freeman’s chain codes and abductive network classifiers. In: Proceedings of the 20th international conference on pattern recognition. Istanbul, Turkey: IEEE, pp 1884–1887. https://doi.org/10.1109/ICPR.2010.464

  • LeCun Y (1998) The MNIST database of handwritten digits [Online]. http://yann.LeCun.com/exdb/mnist/. Accessed 27 May 2019

  • Lee CC, Li YF (2013) Fingertip-writing alphanumeric character recognition based on hidden conditional random field. J Ambient Intell Hum Comput 4(3):285–291. https://doi.org/10.1007/s12652-011-0092-9

    Article  Google Scholar 

  • Liu CL, Suen CY (2009) A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters. Pattern Recogn 42(12):3287–3295. https://doi.org/10.1016/j.patcog.2008.10.007

    Article  MATH  Google Scholar 

  • Mahmoud S (2008) Recognition of writer-independent off-line handwritten Arabic (Indian) numerals using hidden Markov models. Sign Process 88(4):844–857. https://doi.org/10.1016/j.sigpro.2007.10.002

    Article  MATH  Google Scholar 

  • Mahmoud SA, Al-Khatib WG (2011) Recognition of Arabic (Indian) bank check digits using log-gabor filters. Appl Intell 35(3):445–456. https://doi.org/10.1007/s10489-010-0235-2

    Article  Google Scholar 

  • Mahmoud SA, Awaida SM (2009) Recognition of off-line handwritten Arabic (Indian) numerals using multi-scale features and support vector machines vs. hidden markov models. Arab J Sci Eng 34(2B):429–444

    Google Scholar 

  • Maitra DS, Bhattacharya U, Parui SK (2015) CNN based common approach to handwritten character recognition of multiple scripts. In: Proceedings of 13th international conference on document analysis and recognition. Tunis, Tunisia: IEEE, pp 1021–1025. https://doi.org/10.1109/ICDAR.2015.7333916

  • Majhi B, Pujari P (2018) On development and performance evaluation of novel odia handwritten digit recognition methods. Arab J Sci Eng 43(8):3887–3901. https://doi.org/10.1007/s13369-017-2652-6

    Article  Google Scholar 

  • Misra S, Laskar RH (2019) Development of a hierarchical dynamic keyboard character recognition system using trajectory features and scale-invariant holistic modeling of characters. J Ambient Intell Hum Comput 10(12):4901–4923. https://doi.org/10.1007/s12652-019-01189-2

    Article  Google Scholar 

  • Mozaffari S, Faez K, Ziaratban M (2005) Structural decomposition and statistical description of Farsi/Arabic handwritten numeric characters. In: Proceedings of the 8th international conference on document analysis and recognition. Seoul, South Korea: IEEE, pp 237–241. https://doi.org/10.1109/ICDAR.2005.221

  • Mozaffari S, Faez K, Faradji F, Ziaratban M, Golzan SM (2006) A comprehensive isolated Farsi/Arabic character database for handwritten OCR research. In: 10th International workshop on frontiers in handwriting recognition. La Baule, France

  • Nagar R, Mitra SK (2015) Feature extraction based on stroke orientation estimation technique for handwritten numeral. In: Proceedings of the 8th international conference on advances in pattern recognition. Kolkata, India: IEEE, pp 1–6. https://doi.org/10.1109/ICAPR.2015.7050654

  • Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng AY (2011) Reading digits in natural images with unsupervised feature learning. In: Proceedings of the NIPS workshop on deep learning and unsupervised feature learning. Granada, Spain, pp 1–9

  • Pal U, Sharma N, Wakabayashi T, Kimura F (2007) Handwritten numeral recognition of six popular Indian scripts. In: Proceedings of the 9th international conference on document analysis and recognition. Parana, Brazil: IEEE, pp 749–753. https://doi.org/10.1109/ICDAR.2007.4377015

  • Reddy RVK, Rao BS, Raju KP (2018) Handwritten hindi digits recognition using convolutional neural network with RMSprop optimization. In: Proceedings of 2nd international conference on intelligent computing and control systems. Madurai, India: IEEE, pp 45–51. https://doi.org/10.1109/iccons.2018.8662969

  • Saha C, Faisal RH, Rahman MM (2019) Bangla handwritten digit recognition using an improved deep convolutional neural network architecture. In: Proceedings of international conference on electrical, computer and communication engineering. IEEE, pp 1–6. https://doi.org/10.1109/ECACE.2019.8679309

  • Selvi PP, Meyyappan T (2013) Recognition of Arabic numerals with grouping and ungrouping using back propagation neural network. In: Proceedings of international conference on pattern recognition, informatics and mobile engineering. Salem, India: IEEE, pp 322–327. https://doi.org/10.1109/ICPRIME.2013.6496494

  • Sermanet P, Chintala S, LeCun Y (2012) Convolutional neural networks applied to house numbers digit classification. In: Proceedings of 21st international conference on pattern recognition. Tsukuba, Japan: IEEE, pp 3288–3291

  • Solimanpour F, Sadri J, Suen CY (2006) Standard databases for recognition of handwritten digits, numerical strings, legal amounts, letters and dates in Farsi language. In: 10th International workshop on frontiers in handwriting recognition. La Baule, France

  • Trivedi A, Srivastava S, Mishra A, Shukla A, Tiwari R (2018) Hybrid evolutionary approach for devanagari handwritten numeral recognition using convolutional neural network. In: 6th International conference on smart computing and communications. Kurukshetra, India, pp 525–532. https://doi.org/10.1016/j.procs.2017.12.068

  • Tumoohi (2017) Arabic Language to Non-Arabic Speakers [Online]. http://www.tumoohi.org/en/majors/Languages/Arabic-Language-to-Non-Arabic-Speakers. Accessed 27 May 2019

  • Tushar AK, Ashiquzzaman A, Afrin A, Islam MR (2018) A novel transfer learning approach upon Hindi, Arabic, and Bangla numerals using convolutional neural networks. In: Proceedings of international conference on computational vision and bio inspired computing. Springer, Cham, pp 972–981. https://doi.org/10.1007/978-3-319-71767-8_83

  • Venkateswararao P, Murugavalli S (2019) CTC token parsing algorithm using keyword spotting for BLSTM based unconstrained handwritten recognition. J Ambient Intell Hum Comput. https://doi.org/10.1007/s12652-019-01458-0

    Article  Google Scholar 

  • Wang Z, Chang S, Yang Y, Liu D, Huang TS (2016) Studying very low resolution recognition using deep networks. In: Proceedings of 29th international conference on computer vision and pattern recognition. LasVegas, USA, IEEE, pp 4792–4800. https://doi.org/10.1109/CVPR.2016.518

  • Zamani Y, Souri Y, Rashidi H, Kasaei S (2015) Persian handwritten digit recognition by random forest and convolutional neural networks. In: Proceedings of 9th Iranian conference on machine vision and image processing. Tehran, Iran: IEEE, pp 37–40. https://doi.org/10.1109/iranianmvip.2015.7397499

  • Zhan H, Lyu S, Lu Y (2018) Handwritten digit string recognition using convolutional neural network. In: Proceedings of 24th international conference on pattern recognition. IEEE, pp 3729–3734. https://doi.org/10.1109/icpr.2018.8546100

  • Zhao X, Shi X, Zhang S (2015) Facial expression recognition via deep learning. IETE Tech Rev 32(5):347–355. https://doi.org/10.1080/02564602.2015.1017542

    Article  Google Scholar 

  • Zhou J, Wang F, Xu J, Yan Y, Zhu H (2019) A novel character segmentation method for serial number on banknotes with complex background. J Ambient Intell Hum Comput 10(8):2955–2969. https://doi.org/10.1007/s12652-018-0707-5

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Aliah University, Kolkata, India

    Pratik Ahamed, Tauseef Khan & Ayatullah Faruk Mollah

  2. Department of Computer Science and Engineering, Jadavpur University, Kolkata, India

    Soumyadeep Kundu & Ram Sarkar

  3. Department of Electronics and Communication Engineering, Shri Ramswaroop Memorial Group of Professional Colleges, Lucknow, India

    Vikrant Bhateja

Authors
  1. Pratik Ahamed
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Soumyadeep Kundu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tauseef Khan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Vikrant Bhateja
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ram Sarkar
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ayatullah Faruk Mollah
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ayatullah Faruk Mollah.

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

Ahamed, P., Kundu, S., Khan, T. et al. Handwritten Arabic numerals recognition using convolutional neural network. J Ambient Intell Human Comput 11, 5445–5457 (2020). https://doi.org/10.1007/s12652-020-01901-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12652-020-01901-7

Keywords

Search

Navigation