Skip to main content
SpringerLink
Log in

Comparative study on the performance of the state-of-the-art CNN models for handwritten Bangla character recognition

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In the realm of Optical Character Recognition, handwritten character recognition in Bangla is still an unresolved challenge. There have been many breakthroughs in object recognition technology; however, the present approaches may not necessarily give good results for such problems. In this paper, a set of recently developed popular Convolutional Neural Networks (CNNs) is discussed with their application on Bangla handwritten character recognition for the standard dataset ‘Ekush’ and the performance of each of the CNN networks is systematically evaluated. It is obvious that the CNN approaches are more effective than traditional approaches because of their ability to generate discriminative features from raw data. The current study shows the superior performance of CNN models with their recognition rate; which in turn implies that CNN networks are practically suitable to build an automatic Bangla handwritten character recognition system.

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.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Ahmed SB, Naz S, Swati S, Razzak MI (2019) Handwritten urdu character recognition using 1-dimensional blstm classifier. Neural Comput Appl 31:04

    Article  Google Scholar 

  2. Alom MZ, Sidike P, Hasan M, Taha TM, Asari VK (2018) Handwritten bangla character recognition using the state-of-art deep convolutional neural networks. Comput Intell Neurosci 2018:12

    Article  Google Scholar 

  3. Andrew G, Howard MZ, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications

  4. Basu S, Das N, Sarkar R, Kundu M, Nasipuri M, Basu DK (2009) A hierarchical approach to recognition of handwritten bangla characters. Pattern Recog 42(7):1467–1484

    Article  MATH  Google Scholar 

  5. Bhagyasree PV, James A, Bisna ND, Vipin Kumar KS (2022) Handwritten cursive english character recognition using dag-cnn. In: Chakravarthy VVSSS, Flores-Fuentes W, Bhateja V, Biswal BN (eds) Advances in micro-electronics, embedded systems and IoT. Springer, Singapore, pp 89–102

  6. Bhattacharya U, Shridhar M, Parui S, Sen P, Chaudhuri B (2012) Offline recognition of handwritten bangla characters: an efficient two-stage approach. Pattern Anal Appl 15:445–458

    Article  MathSciNet  Google Scholar 

  7. Bhattacharyya A, Chakraborty R, Saha S, Sen S, Sarkar R, Roy K (2022) A two-stage deep feature selection method for online handwritten bangla and devanagari basic character recognition. SN Comput Sci 3(4):1–16

    Article  Google Scholar 

  8. Bhowmik T, Ghanty P, Roy A, Parui S (2009) Svm-based hierarchical architectures for handwritten bangla character recognition. Doc Anal Recognit 12:97–108

    Article  Google Scholar 

  9. Bunke H, Bengio S, Vinciarelli A (2004) Offline recognition of unconstrained handwritten texts using hmms and statistical language models. IEEE Trans Pattern Anal Mach Intell 26(6):709–720

    Article  Google Scholar 

  10. Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 1800–1807

  11. Cireşan D, Meier U (2015) Multi-column deep neural networks for offline handwritten chinese character classification. In: 2015 international joint conference on neural networks (IJCNN), pp 1–6

  12. Das N, Basu S, Sarkar R, Kundu M, Nasipuri M, Basu D (2009) An improved feature descriptor for recognition of handwritten bangla alphabet. In: Proc. of international conference on signal and image processing (ICSIP-2009), India, p 01

  13. Das N, Das B, Sarkar R, Basu S, Kundu M, Nasipuri M (2010) Handwritten bangla basic and compound character recognition using mlp and svm classifier. J Comput 2:02

    Google Scholar 

  14. Das A, Roy S, Bhattacharya U, Parui SK (2018) Document image classification with intra-domain transfer learning and stacked generalization of deep convolutional neural networks. In: 2018 24Th international conference on pattern recognition (ICPR), IEEE, pp 3180–3185

  15. Dey R, Balabantaray RC, Mohanty S (2022) Offline odia handwritten character recognition with a focus on compound characters. Multimed Tools Appl 81:10469–10495

    Article  Google Scholar 

  16. Ghosh T, Abedin Md, Chowdhury SM, Yousuf MA, Ha-zul M (2019) A comprehensive review on recognition techniques for bangla handwritten characters. In: 2019 international conference on bangla speech and language processing (ICBSLP), pp 1–6

  17. Guha R, Das N, Kundu M, Nasipuri M, Santosh KC (2020) Devnet: an efficient cnn architecture for handwritten devanagari character recognition. Int J Pattern Recog Artif Intell 34(12):2052009

    Article  Google Scholar 

  18. Halder C, Obaidullah SM, Roy K (2015) Effect of writer information on bangla handwritten character recognition. In: 2015 fifth national conference on computer vision, pattern recognition, image processing and graphics (NCVPRIPG), IEEE, pp 1–4

  19. Hasasneh A, Salman N, Eleyan D (2019) Towards offline arabic handwritten character recognition based on unsupervised machine learning methods: a perspective study. Int J Comput Acad Res 1:1–8

    Google Scholar 

  20. He Kaiming, Zhang Xiangyu, Ren Shaoqing, Sun Jian (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  21. Hu M, Li Z, Shen Y, Liu A, Liu G, Zheng K, Zhao L (2017) Cnn-iets: a cnn-based probabilistic approach for information extraction by text segmentation. In: Lim E-P, Winslett M, Sanderson M, Fu AW-C, Sun J, Culpepper JS, Lo E, Ho JC, Donato D, Agrawal R, Zheng Y, Castillo C, Sun A, Tseng VS, Li C (eds) CIKM’17 proceedings of the 2017 ACM on conference on information and knowledge management, ACM, pp 1159–1168

  22. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE Computer Society, Los Alamitos, CA, USA, pp 2261–2269

  23. Indian A, Bhatia K, Kumar K (2022) Offline handwritten hindi character recognition using deep learning with augmented dataset. In: Cyber security in intelligent computing and communications, Springer, pp 129–141

  24. Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Bach F, Blei D (eds) Proceedings of the 32nd international conference on machine learning, vol 37. Proceedings of Machine Learning Research PMLR, pp 448–456

  25. Islam MS, Rahman MM, Rahman MH, Rivolta MW, Aktaruzzaman M (2022) Ratnet: a deep learning model for bengali handwritten characters recognition. Multimed Tools Appl 81:10631–10651

    Article  Google Scholar 

  26. Kahan S, Pavlidis T, Baird HS (1987) On the recognition of printed characters of any font and size. IEEE Trans Pattern Anal Mach Intell PAMI-9(2):274–288

    Article  Google Scholar 

  27. Kaur H, Kumar M (2021a) Offline handwritten Gurumukhi word recognition using extreme Gradient Boosting methodology. Soft Comput 25(6):4451–4464. https://doi.org/10.1007/s00500-020-05455-w

    Article  Google Scholar 

  28. Kaur H, Kumar M (2021b) On the recognition of offline handwritten word using holistic approach and adaboost methodology. Multimed Tools Appl 80(7):11155–11175. https://doi.org/10.1007/s11042-020-10297-7

    Article  Google Scholar 

  29. Krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks. Neural Inf Process Syst 25:01

    Google Scholar 

  30. Kumar S, Kumar K (2018) Lsrc: Lexicon star rating system over cloud. In: 2018 4Th international conference on recent advances in information technology (RAIT), IEEE, pp 1–6

  31. Kumar Krishan, Kurhekar Manish (2017) Sentimentalizer: docker container utility over cloud. In: 2017 Ninth international conference on advances in pattern recognition (ICAPR), IEEE, pp 1–6

  32. Kumar M, Narang S, Jindal M (2021) Deepnetdevanagari: a deep learning model for devanagari ancient character recognition. Multimed Tools Appl 80:20671–20686

    Article  Google Scholar 

  33. Kumar Avanish, Purohit Kaustubh, Kumar Krishan (2019) Stock price prediction using recurrent neural network and long short-term memory. In: International conference on deep learning, artificial intelligence and robotics, Springer, 153–160

  34. Kumar K, Shrimankar DD (2017) F-des: fast and deep event summarization. IEEE Trans Multimed 20(2):323–334

    Article  Google Scholar 

  35. Kumar Krishan, Shrimankar Deepti D (2018) Deep event learning boost-up approach: delta. Multimed Tools Appl 77(20):26635–26655

    Article  Google Scholar 

  36. Kumari S, Singh M, Kumar K (2019) Prediction of liver disease using grouping of machine learning classifiers. In: International conference on deep learning, artificial intelligence and robotics, Springer, pp 339–349

  37. Lincy Babitha, Gayathri Rajagopal (2020) Optimally configured convolutional neural network for tamil handwritten character recognition by improved lion optimization model. Multimed Tools Appl 10:1–27

    Google Scholar 

  38. Malarvizhi N, Selvarani P, Chelliah PR (2020) Adaptive fuzzy genetic algorithm for multi biometric authentication. Multimed Tools Appl 79:04

    Article  Google Scholar 

  39. Mushtaq F, Misgar MM, Kumar M, Khurana SS (2021) Urdudeepnet: offline handwritten urdu character recognition using deep neural network. Neural Comput Appl 33:15229–15252

    Article  Google Scholar 

  40. Negi Alok, Krishan K, Chauhan P (2021) Deep learning-based image classifier for malaria cell detection. Machine Learning for Healthcare Applications :187–197

  41. Negi A, Chauhan P, Kumar K, Rajput RS (2020) Face mask detection classifier and model pruning with keras-surgeon. In: 2020 5th IEEE international conference on recent advances and innovations in engineering (ICRAIE), IEEE, pp 1–6

  42. Negi A, Kumar K (2021) Classification and detection of citrus diseases using deep learning. In: Data science and its applications. Chapman and Hall/CRC, New York, pp 63–85

  43. Negi A, Kumar K (2021) Face mask detection in real-time video stream using deep learning. Comput Intell Healthc Informat :255–268

  44. Negi A, Kumar K, Chaudhari NS, Singh N, Chauhan P (2021) Predictive analytics for recognizing human activities using residual network and fine-tuning. In: Srirama SN, Lin JC-W, Bhatnagar R, Agarwal S, Reddy PK (eds) Big data analytics. Springer, Cham, pp 296–310

  45. Negi A, Kumar K, Chauhan P (2021) Deep neural network-based multi-class image classification for plant diseases. In: Agricultural informatics: automation using the IoT and machine learning, pp 117–129

  46. Obaidullah SM, Halder C, Das N, Roy K (2016) Pwdb_13: a corpus of word-level printed document images from thirteen official indic scripts. In: Das S, Pal T, Kar S, Satapathy SC, Mandal JK (eds) Proceedings of the 4th international conference on frontiers in intelligent computing: theory and applications (FICTA) 2015. Springer, New Delhi, pp 233–242

  47. Obaidullah SM, Halder C, Santosh KC, Das N, Roy K (2017) Phdindic_11: page-level handwritten document image dataset of 11 official indic scripts for script identification. Multimed Tools Appl 77:1643–1678

    Article  Google Scholar 

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

  49. Phamtoan D, Vo-Van T (2020) Automatic fuzzy genetic algorithm in clustering for images based on the extracted intervals. Multimed Tools Appl 10:1–23

    Google Scholar 

  50. Pramanik R, Bag S (2017) Shape decomposition-based handwritten compound character recognition for bangla ocr. J Vis Commun Image Represent 50:123–134

    Article  Google Scholar 

  51. Rabby ASA, SadekaHaque Md, Abujar S, Hossain S, Islam S (2018) Ekush: a multipurpose and multitype comprehensive database for online off-line bangla handwritten characters. In: Recent trends in image processing and pattern recognition, pp 149–158

  52. Rakshit P, Halder C, Obaidullah SM, Roy K (2021) A survey on line segmentation techniques for indic scripts. In: Santosh KC, Gawali B (eds) Recent trends in image processing and pattern recognition. Springer, Singapore, pp 511–522

  53. Rakshit P, Halder C, Roy K (2019) An approach toward character recognition of Bangla handwritten isolated characters. https://doi.org/10.1201/9780429277573-2. Chapman and Hall/CRC, New York, pp 15–28

  54. Ren H, Wang W, Liu C (2019) Recognizing online handwritten chinese characters using rnns with new computing architectures. Pattern Recog 93:04

    Article  Google Scholar 

  55. Rostami M, Berahmand K, Nasiri E, Forouzandeh S (2021) Review of swarm intelligence-based feature selection methods. Eng Appl Artif Intell 104210:100

    Google Scholar 

  56. Rostami M, Forouzandeh S, Berahmand K, Soltani M, Shahsavari M, Oussalah M (2022) Gene selection for microarray data classification via multi-objective graph theoretic-based method. Artif Intell Med 123:102228

    Article  Google Scholar 

  57. Roy S, Das N, Kundu M, Nasipuri M (2017) Handwritten isolated bangla compound character recognition: a new benchmark using a novel deep learning approach. Pattern Recog Lett 90:03

    Article  Google Scholar 

  58. Roy A, Mazumder N, Das N, Sarkar R, Basu S, Nasipuri M (2012) A new quad tree based feature set for recognition of handwritten bangla numerals. In: 2012 IEEE international conference on engineering education: innovative practices and future trends (AICERA), IEEE, pp 1–6

  59. Sachdeva J, Mittal S (2022) Handwritten offline devanagari compound character recognition using cnn. In: Proceedings of data analytics and management. Springer, Singapore, pp 211–220

  60. Saha S, Puja NS (2018) A lightning fast approach to classify bangla handwritten characters and numerals using newly structured deep neural network. Procedia Comput Sci 132:1760–1770

    Article  Google Scholar 

  61. Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 4510–4520

  62. Sarkhel R, Saha AK, Das N (2015) An enhanced harmony search method for bangla handwritten character recognition using region sampling. In: 2015 IEEE 2Nd international conference on recent trends in information systems (reTIS), IEEE, pp 325–330

  63. Sen S, Bhattacharyya A, Das A, Sarkar R, Roy K (2017) Design of novel feature vector for recognition of online handwritten bangla basic characters. In: Mandal JK, Satapathy SC, Sanyal MK, Bhateja V (eds) Proceedings of the first international conference on intelligent computing and communication. Springer, Singapore, pp 485–494

  64. Shahariar AKM, Rabby A, Haque S, Abujar S, Hossain SA (2018) Ekushnet: using convolutional neural network for bangla handwritten recognition. Procedia Comput Sci 143:603–610. 8th International Conference on Advances in Computing & Communications (ICACC-2018)

    Article  Google Scholar 

  65. Sharma S, Kumar P, Kumar K (2017) Lexer: lexicon based emotion analyzer. In: International conference on pattern recognition and machine intelligence, Springer, pp 373–379

  66. Sharma S, Kumar K, Singh N (2017) D-fes: deep facial expression recognition system. In: 2017 conference on information and communication technology (CICT), pp 1–6

  67. Shuvo SN, Hasan F, Ahmed MU, Hossain SA, Abujar S (2021) Mathnet: using cnn bangla handwritten digit, mathematical symbols, and trigonometric function recognition. In: Borah S, Pradhan R, Dey N, Gupta P (eds) Soft computing techniques and applications. Springer, Singapore, pp 515–523

  68. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Bengio Y, LeCun Y (eds) 3rd international conference on learning representations, ICLR 2015, Conference Track Proceedings

  69. Singh P, Sarkar R, Nasipuri M (2016) A study of moment based features on handwritten digit recognition. Appl Comput Intell Soft Comput 2016:1–17

    Google Scholar 

  70. Singh H, Sharma RK, Singh VP, Kumar M (2021) Recognition of online handwritten gurmukhi characters using recurrent neural network classifier. Soft Comput 25:04

    Article  Google Scholar 

  71. Szegedy C, Ioffe S, Vanhoucke V, Alemi A (2017) Inception-v4 inception-resnet and the impact of residual connections on learning. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pp 4278–4284

  72. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2015) Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2818–2826, DOI https://doi.org/10.1109/CVPR.2016.308

  73. Tan M, Le Q (2019) EfficientNet: rethinking model scaling for convolutional neural networks. In: Chaudhuri K, Salakhutdinov R (eds) Proceedings of the 36th international conference on machine learning, volume 97 of Proceedings of Machine Learning Research, PMLR, pp 6105–6114

  74. Ukil S, Ghosh S, Obaidullah S, Santosh K, Roy K, Das N (2020) Improved word-level handwritten indic script identification by integrating small convolutional neural networks. Neural Comput Appl 32:04

    Article  Google Scholar 

  75. Vijayvergia A, Kumar K (2018) Star: rating of reviews by exploiting variation in emotions using transfer learning framework. In: 2018 conference on information and communication technology (CICT), IEEE, pp 1–6

  76. Yin W, Mo Y, Xiang B, Zhou B, Schütze H (2016) Simple question answering by attentive convolutional neural network. In: Proceedings of COLING 2016, the 26th international conference on computational linguistics: technical papers, pp 1746–1756

  77. Zoph B, Vasudevan V, Shlens J, Le QV (2018) Learning transferable architectures for scalable image recognition. In: 2018 IEEE/CVF conference on computer vision and pattern recognition. https://doi.org/10.1109/CVPR.2018.00907, pp 8697–8710

Download references

Author information

Authors and Affiliations

  1. Maheshtala College, Kolkata, 141, India

    Payel Rakshit

  2. Future Institute of Engineering and Management, Kolkata, 154, India

    Somnath Chatterjee

  3. Ramakrishna Mission Vivekananda Centenary College, Kolkata, 118, India

    Chayan Halder

  4. Techno Main Salt Lake, Kolkata, 700091, India

    Shibaprasad Sen

  5. Aliah University, Kolkata, 156, India

    Sk Md Obaidullah

  6. West Bengal State University, Kolkata, 126, India

    Kaushik Roy

Authors
  1. Payel Rakshit
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Somnath Chatterjee
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chayan Halder
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shibaprasad Sen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Sk Md Obaidullah
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kaushik Roy
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kaushik Roy.

Ethics declarations

Conflict of Interests

The authors declare that they have no conflict of interest.

Additional information

Publisher’s note

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

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rakshit, P., Chatterjee, S., Halder, C. et al. Comparative study on the performance of the state-of-the-art CNN models for handwritten Bangla character recognition. Multimed Tools Appl 82, 16929–16950 (2023). https://doi.org/10.1007/s11042-022-13909-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-13909-6

Keywords

Search

Navigation