[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to main content
Springer Nature Link
Log in

A new Arabic handwritten character recognition deep learning system (AHCR-DLS)

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Optical character recognition for the English text may be considered one of the most important research topics, whether, printed or handwritten. Although excellent results have been reached in the English text, there is a lack of this type of research in the Arabic text. This is because of the nature of the Arabic alphabet, and the multiplicity of forms of the same letter. Arabic handwritten character recognition (AHCR) systems involve several issues, and challenges from finding a suitable, and public Arabic handwritten text dataset phase to recognition, and classification phase passing through segmentation, and feature extraction phases. The paper objectives are: Firstly, a large, and complex Arabic handwritten characters’ dataset (HMBD) is presented for training, testing, and validation phases, as well as, discussing its collection, preparation, cleaning, and preprocessing. Secondly, we introduce a deep learning (DL) system with two convolutional neural network (CNN) architectures (named HMB1 and HMB2); with the appliance of optimization, regularization, and dropout techniques. This system can serve as a baseline for future research on handwritten Arabic text. Different performance metrics were calculated such as accuracy, recall, precision, and F1. 16 experiments were applied to the described system using HMBD, and another two datasets: CMATER, and AIA9k. Experiments’ results were captured and compared to study the effects of weight initializers, optimizers, data augmentation, and regularization on overfitting, and accuracy. He Uniform weight initializer and AdaDelta optimizer reported the highest accuracies. Data augmentation showed an improvement in the accuracies. HMB1 reported testing accuracy of 98.4% with 865,840 records using augmentation on HMBD. CMATER and AIA9k datasets were used for validating the generalization. Data augmentation was applied, and the best results were 100%, and 99.0% for testing accuracies, respectively. A cross-over validation between the described architectures, and a previous state-of-the-art architecture, and dataset was performed in two phases. First, the previous control architecture cannot generalize for the presented dataset in the current study. Second, the study described architectures generalize for the control dataset, with higher accuracies (97.3%, and 96.8% for HMB1, and HMB2, respectively), than the reported accuracy in the selected control study.

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
£29.99 /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 includes VAT (United Kingdom)

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
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24
Fig. 25
Fig. 26
Fig. 27
Fig. 28
Fig. 29
Fig. 30
Fig. 31
Fig. 32
Fig. 33
Fig. 34
Fig. 35
Fig. 36
Fig. 37
Fig. 38
Fig. 39
Fig. 40
Fig. 41
Fig. 42
Fig. 43
Fig. 44
Fig. 45
Fig. 46
Fig. 47
Fig. 48
Fig. 49
Fig. 50

Similar content being viewed by others

Explore related subjects

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

Abbreviations

AdaDelta:

An adaptive learning rate method

Adam:

A method for stochastic optimization

AHCR:

Arabic handwritten character recognition

AHCR-DLS:

Arabic handwritten character recognition deep learning system

CNN:

Convolutional neural network

DL:

Deep learning

ReLU:

Rectified linear unit

SGD:

Stochastic gradient descent

UN:

United Nations

References

  1. Ridout S (2019) Complete list of Arabic speaking countries—2020 update. http://istizada.com/complete-list-of-arabic-speaking-countries-2014/. Accessed 18-12-2019

  2. Versteegh K (2014) Arabic language. Edinburgh University Press, Edinburgh

    Google Scholar 

  3. Suleiman Y (2003) The Arabic language and national identity. Edinburgh University Press, Edinburgh

    Google Scholar 

  4. Shaalan K, Al-Sheikh S, Oroumchian F (2012) Query expansion based-on similarity of terms for improving Arabic information retrieval. In: International conference on intelligent information processing, pp 167–176

  5. El-Desouky AI, Salem MM, El-Gwad AOA, Arafat H (1991) A handwritten Arabic character recognition technique for machine reader. In: Third international conference on software engineering for real time systems, pp 212–216

  6. Shirko O, Omar N, Arshad H, Albared M (2010) Machine translation of noun phrases from Arabic to English using transfer-based approach. J Comput Sci 6:350

    Article  Google Scholar 

  7. Klatt DH (1987) Review of text-to-speech conversion for English. J Acoust Soc Am 82:737–793

    Article  Google Scholar 

  8. Bijl D, Hyde-Thomson H (2001) Speech to text conversion. Google Patents

  9. 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, 2019, pp 299–309

  10. Deng D, Liu H, Li X, Cai D (2018) Pixellink: detecting scene text via instance segmentation. In: Thirty-second AAAI conference on artificial intelligence

  11. Korns MF, May T (2019) Strong typing, swarm enhancement, and deep learning feature selection in the pursuit of symbolic regression-classification. In: Genetic programming theory and practice XVI. Springer, pp 59–84

  12. Howard J, Ruder S (2018) Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146

  13. Wang Y, Xu W (2018) Leveraging deep learning with LDA-based text analytics to detect automobile insurance fraud. Decis Support Syst 105:87–95

    Article  Google Scholar 

  14. Chatterjee A, Gupta U, Chinnakotla MK, Srikanth R, Galley M, Agrawal P (2019) Understanding emotions in text using deep learning and big data. Comput Hum Behav 93:309–317

    Article  Google Scholar 

  15. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444

    Article  Google Scholar 

  16. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems 25 (NIPS 2012)

  17. Habibi Aghdam H, Jahani Heravi E (2017) Convolutional neural networks. In: Guide to convolutional neural networks: a practical application to traffic-sign detection and classification. Springer, Cham, pp 85–130

  18. Govindan V, Shivaprasad A (1990) Character recognition—a review. Pattern Recognit 23:671–683

    Article  Google Scholar 

  19. Hamid A, Haraty R (2001) A neuro-heuristic approach for segmenting handwritten Arabic text. In: Proceedings ACS/IEEE international conference on computer systems and applications, 2001, pp 110–113

  20. Pal U, Chaudhuri B (2004) Indian script character recognition: a survey. Pattern Recognit 37:1887–1899

    Article  Google Scholar 

  21. Biadsy F, Saabni R, El-Sana J (2011) Segmentation-free online Arabic handwriting recognition. Int J Pattern Recognit Artif Intell 25:1009–1033

    Article  Google Scholar 

  22. Tappert CC, Suen CY, Wakahara T (1990) The state of the art in online handwriting recognition. IEEE Trans Pattern Anal Mach Intell 12:787–808

    Article  Google Scholar 

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

    Article  Google Scholar 

  24. El-Sawy A, Loey M, Hazem E (2017) Arabic handwritten characters recognition using convolutional neural network. WSEAS Trans Comput Res 5:11–19

    Google Scholar 

  25. Younis KS (2017) Arabic handwritten character recognition based on deep convolutional neural networks. Jordan J Comput Inf Technol 3:2017

    Google Scholar 

  26. El-Melegy M, Abdelbaset A, Abdel-Hakim A, El-Sayed G (2019) Recognition of Arabic handwritten literal amounts using deep convolutional neural networks, Cham, pp 169–176

  27. Torki M, Husseiny ME, Elsallamy A, Fayyaz M, Yaser S (2014) Window-based descriptors for Arabic handwritten alphabet recognition: a comparative study on a novel dataset. arXiv preprint arXiv:1411.3519

  28. Loey M (31-08-2019) Arabic handwritten characters dataset. https://www.kaggle.com/mloey1/ahcd1

  29. Alamri H, Sadri J, Suen CY, Nobile N (2008) A novel comprehensive database for Arabic off-line handwriting recognition. In: Proceedings of 11th international conference on frontiers in handwriting recognition, ICFHR, 2008, pp 664–669

  30. Eikvil L (1993) OCR-optical character recognition. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.25.3684

  31. Lensu A (2002) Computationally intelligent methods for qualitative data analysis. No. 23. University of Jyväskylä. https://www.semanticscholar.org/paper/Anssi-Lensu-Computationally-Intelligent-Methods-for-Lensu-Olsbo/f58234bfae6de53aa39110ed69f3438c59cb0304

  32. Vadwala MA, Suthar MK, Karmakar MY, Thakkar N (2017) Survey paper on different speech recognition algorithm: challenges and techniques. Int J Comput Appl 175(1):31–36

  33. Lawgali A (2015) A survey on Arabic character recognition. https://doi.org/10.14257/ijsip.2015.8.2.37

  34. Tanner MA, Wong WH (1987) The calculation of posterior distributions by data augmentation. J Am Stat Assoc 82:528–540

    Article  MathSciNet  Google Scholar 

  35. Frühwirth-Schnatter S (1994) Data augmentation and dynamic linear models. J Time Ser Anal 15:183–202

    Article  MathSciNet  Google Scholar 

  36. Hamida S, Cherradi B, Ouajji H, Raihani A (2020) Convolutional neural network architecture for offline handwritten characters recognition. In: International conference Europe Middle East & North Africa information systems and technologies to support learning. Springer, Cham, pp 368–377. https://doi.org/10.1007/978-3-030-36778-7_41

  37. Neri CG, Villegas OOV, Sánchez VGC, Nandayapa M, Azuela JHS (2020) A convolutional neural network for handwritten digit recognition. Int J Comb Optim Probl Inform 11:97–105

    Google Scholar 

  38. Clevert D-A, Unterthiner T, Hochreiter S (2015) Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289

  39. Younis K (2018) Arabic handwritten character recognition based on deep convolutional neural networks. Jordanian J Comput Inform Technol 3(3)

  40. Deng L (2012) The mnist database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Process Mag 29:141–142

    Article  Google Scholar 

  41. Torrey L, Shavlik J (2010) Transfer learning. In: Handbook of research on machine learning applications and trends: algorithms, methods, and techniques. IGI Global, 2010, pp 242–264

  42. Pan SJ (2009) Q. J. I. T. o. k. Yang, and d. engineering, A survey on transfer learning, vol 22, pp 1345–1359

  43. Kim Y (2014) Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882

  44. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958

    MathSciNet  MATH  Google Scholar 

  45. Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167

  46. Hidaka A, Kurita T (2017) Consecutive dimensionality reduction by canonical correlation analysis for visualization of convolutional neural networks. In: Proceedings of the ISCIE international symposium on stochastic systems theory and its applications, vol 2017. The ISCIE symposium on stochastic systems theory and its applications 2017

  47. Undrestanding Convolutional Layers in Convolutional Neural Networks (CNNs). http://machinelearninguru.com/computer_vision/basics/convolution/convolution_layer.html

  48. Mallick S, Nayak S (2018, May 22) Number of parameters and tensor sizes in a convolutional neural network (CNN). https://www.learnopencv.com/number-of-parameters-and-tensor-sizes-in-convolutional-neural-network/

  49. van Laarhoven T (2017) L2 regularization versus batch and weight normalization. arXiv preprint arXiv:1706.05350

  50. Hara K, Saito D, Shouno H (2015) Analysis of function of rectified linear unit used in deep learning. In: 2015 international joint conference on neural networks (IJCNN), pp 1–8

  51. Dunne RA, Campbell NA (1997) On the pairing of the softmax activation and cross-entropy penalty functions and the derivation of the softmax activation function. In: Proceedings of 8th Australian conference on neural networks, Melbourne, 1997, p 185

  52. Koturwar S, Merchant S (2017) Weight initialization of deep neural networks (DNNS) using data statistics. arXiv preprint arXiv:1710.10570

  53. Sutskever I, Martens J, Dahl G, Hinton G (2013) On the importance of initialization and momentum in deep learning. In: International conference on machine learning, 2013, pp 1139–1147

  54. LeCun YA, Bottou L, Orr GB, Müller K-R (2012) Efficient backprop. In: Neural networks: tricks of the trade. Springer, pp 9–48

  55. Klambauer G, Unterthiner T, Mayr A, Hochreiter S (2017) Self-normalizing neural networks. In: Advances in neural information processing systems, pp 971–980

  56. 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

  57. He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, 2015, pp 1026–1034

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

  59. Reddi SJ, Kale S, Kumar S (2019) On the convergence of adam and beyond. arXiv preprint arXiv:1904.09237

  60. Zeiler MD (2012) ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701

  61. Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12:2121–2159

    MathSciNet  MATH  Google Scholar 

  62. Bottou L (2012) Stochastic gradient descent tricks. In: Neural networks: tricks of the trade. Springer, pp 421–436

  63. Gulli A, Pal S (2017) Deep learning with Keras. Packt Publishing Ltd, Birmingham

    Google Scholar 

  64. Bisong E (2019) Google colaboratory. In: Building machine learning and deep learning models on Google cloud platform. Springer, pp 59–64

  65. Joshi R (2016, September 9) Accuracy, precision, recall & F1 score: interpretation of performance measures. https://blog.exsilio.com/all/accuracy-precision-recall-f1-score-interpretation-of-performance-measures/

  66. Accuracy, Precision, Recall and F1 Scores for Lawyers. (October 10, 2019). https://lawtomated.com/accuracy-precision-recall-and-f1-scores-for-lawyers/

  67. Nicholson C. Evaluation metrics for machine learning—accuracy, precision, recall, and F1 defined. https://pathmind.com/wiki/accuracy-precision-recall-f1

  68. Chase Lipton Z, Elkan C, Narayanaswamy B (2014) Thresholding classifiers to maximize F1 score. arXiv preprint arXiv:1402.1892

  69. Powers DM (2011) Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. https://dspace2.flinders.edu.au/xmlui/handle/2328/27165

  70. Goutte C, Gaussier E (2005) A probabilistic interpretation of precision, recall and F-score, with implication for evaluation, vol 3408

  71. Reed R, Marks RJ II (1999) Neural smithing: supervised learning in feedforward artificial neural networks. MIT Press, Cambridge

    Book  Google Scholar 

  72. Al-Ayyoub M, Nuseir A, Alsmearat K, Jararweh Y, Gupta B (2018) Deep learning for Arabic NLP: a survey. J Comput Sci 26:522–531

    Article  Google Scholar 

  73. Abdelazeem S, El-Sherif E. The Arabic handwritten digits databases: ADBase & MADBase. http://datacenter.aucegypt.edu/shazeem/

  74. Alani A (2017) Arabic handwritten digit recognition based on restricted boltzmann machine and convolutional neural networks. Information 8:142

    Article  Google Scholar 

  75. Ashiquzzaman A, Tushar AK, Rahman A (2017) Applying data augmentation to handwritten arabic numeral recognition using deep learning neural networks, arXiv preprint arXiv:1708.05969

Download references

Acknowledgements

We would like to express gratitude and appreciation to Prof. Dr. Magdy H. Balaha, who provided guidance, and assistance in this research work and to the Mansoura university volunteers who decided to cooperate in the dataset construction.

Author information

Authors and Affiliations

  1. Computers and Systems Engineering Department, Faculty of Engineering, Mansoura University, Mansoura, Egypt

    Hossam Magdy Balaha, Hesham Arafat Ali, Mohamed Saraya & Mahmoud Badawy

  2. Department of Computer Science and Informatics, Taibah University, Al Medina Al Munawara, Saudi Arabia

    Mahmoud Badawy

Authors
  1. Hossam Magdy Balaha
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hesham Arafat Ali
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mohamed Saraya
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mahmoud Badawy
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hossam Magdy Balaha.

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

Balaha, H.M., Ali, H.A., Saraya, M. et al. A new Arabic handwritten character recognition deep learning system (AHCR-DLS). Neural Comput & Applic 33, 6325–6367 (2021). https://doi.org/10.1007/s00521-020-05397-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-020-05397-2

Keywords

Search

Navigation