Abstract
Bengali is the sixth most popular spoken language in the world. Computerized detection of handwritten Bengali (Bangla Lekha) character is very difficult due to the diversity and veracity of characters. In this paper, we have proposed a modified state-of-the-art deep learning to tackle the problem of Bengali handwritten character recognition. This method used the lesser number of iterations to train than other comparable methods. The transfer learning on Resnet-50 deep convolutional neural network model is used on pretrained ImageNet dataset. One cycle policy is modified with varying the input image sizes to ensure faster training. Proposed method executed on BanglaLekha-Isolated dataset for evaluation that consists of 84 classes (50 Basic, 10 Numerals and 24 Compound Characters). We have achieved 97.12% accuracy in just 47 epochs. Proposed method gives very good results in terms of epoch and accuracy compare to other recent methods by considering number of classes. Without ensembling, proposed solution achieves state-of-the-art result and shows the effectiveness of ResNet-50 for classification of Bangla HCR.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alif, M.A.R., Ahmed, S., Hasan, M.A.: Isolated bangla handwritten character recognition with convolutional neural network. In: 2017 20th International Conference of Computer and Information Technology (ICCIT), pp. 1–6. IEEE, Dhaka, December 2017. http://ieeexplore.ieee.org/document/8281823/
Alom, M.Z., Sidike, P., Hasan, M., Taha, T.M., Asari, V.K.: Handwritten Bangla character recognition using the state-of-the-art deep convolutional neural networks. Comput. Intell. Neurosci. 2018, 1–13 (2018). https://www.hindawi.com/journals/cin/2018/6747098/
Bhattacharya, U., Shridhar, M., Parui, S.K.: On recognition of handwritten bangla characters. In: Kalra, P.K., Peleg, S. (eds.) ICVGIP 2006. LNCS, vol. 4338, pp. 817–828. Springer, Heidelberg (2006). https://doi.org/10.1007/11949619_73
Biswas, M., et al.: BanglaLekha-Isolated: a multi-purpose comprehensive dataset of Handwritten Bangla Isolated characters. Data Brief 12, 103–107 (2017)
Ciresan, D.: Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification, pp. 1–6. IEEE, Killarney (2015). http://ieeexplore.ieee.org/document/7280516/
Das, N., Basu, S., Sarkar, R., Kundu, M., Nasipuri, M., Basu, D.K.: An Improved Feature Descriptor for Recognition of Handwritten Bangla Alphabet. arXiv:1501.05497 [cs], January 2015
Forkan, A.R.M., Saha, S., Rahman, M.M., Sattar, M.A.: Recognition of conjunctive Bangla characters by artificial neural network. In: 2007 International Conference on Information and Communication Technology, ICICT 2007, pp. 96–99. IEEE (2007)
Hasnat, M.A., Habib, S.M., Khan, M.: A high performance domain specific OCR For Bangla script. In: Sobh, T., Elleithy, K., Mahmood, A., Karim, M.A. (eds.) Novel Algorithms and Techniques In Telecommunications. Automation and Industrial Electronics. Springer, Dordrecht (2008). https://doi.org/10.1007/978-1-4020-8737-0_31
Hassan, T., Khan, H.A.: Handwritten Bangla numeral recognition using local binary pattern. In: 2015 International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), pp. 1–4. IEEE (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition. arXiv:1512.03385 [cs] , December 2015
Howard, J., Ruder, S.: Universal Language Model Fine-tuning for Text Classification. arXiv:1801.06146 [cs, stat], January 2018
Ioffe, S., Szegedy, C.: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv:1502.03167 [cs], February 2015
Kim, I.-J., Xie, X.: Handwritten Hangul recognition using deep convolutional neural networks. IJDAR 18(1), 1–13 (2014). https://doi.org/10.1007/s10032-014-0229-4
Suen, C.Y.: A new benchmark on the recognition of handwritten bangla and Farsi numeral characters. Pattern Recogn. 42(12), 3287–3295 (2009)
Loshchilov, I., Hutter, F.: SGDR: Stochastic Gradient Descent with Warm Restarts. arXiv:1608.03983 [cs, math], August 2016
Loshchilov, I., Hutter, F.: Fixing Weight Decay Regularization in Adam. arXiv:1711.05101 [cs, math], November 2017
Majid, N., Smith, E.H.B.: Introducing the Boise state Bangla handwriting dataset and an efficient offline recognizer of isolated Bangla characters. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 380–385. IEEE (2018)
Das, N., Basu, S., Saha, P.K., Sarkar, R., Kundu, M., Nasipuri, M.: Handwritten Bangla character recognition using a soft computing paradigm embedded in two pass approach. Pattern Recogn. 48(6), 2054–2071 (2015). https://doi.org/10.1016/j.patcog.2014.12.011
Purkaystha, B., Datta, T., Islam, M.S.: Bengali handwritten character recognition using deep convolutional neural network. In: 2017 20th International Conference of Computer and Information Technology (ICCIT), pp. 1–5. IEEE (2017)
Rahman, M.M., Akhand, M.A.H., Islam, S., Chandra Shill, P., Hafizur Rahman, M.M.: Bangla handwritten character recognition using convolutional neural network. Int. J. Image Graph. Signal Process. 7(8), 42–49 (2015). http://www.mecs-press.org/ijigsp/ijigsp-v7-n8/v7n8-5.html
Ray, A., Chatterjee, B.: Design of a nearest neighbour classifier system for Bengali character recognition. IETE J. Res. 30(6), 226–229 (1984). http://www.tandfonline.com/doi/full/10.1080/03772063.1984.11453273
Roy, S., Das, N., Kundu, M., Nasipuri, M.: Handwritten isolated Bangla compound character recognition: a new benchmark using a novel deep learning approach. Pattern Recogn. Lett. 90, 15–21 (2017). https://linkinghub.elsevier.com/retrieve/pii/S0167865517300703
Russakovsky, O., et al.: ImageNet Large Scale Visual Recognition Challenge. arXiv:1409.0575 [cs], September 2014
Saha, S., Saha, N.: A lightning fast approach to classify Bangla handwritten characters and numerals using newly structured deep neural network. Procedia Comput. Sci. 132, 1760–1770 (2018)
Sarkhel, R., Das, N., Saha, A.K., Nasipuri, M.: A multi-objective approach towards cost effective isolated handwritten Bangla character and digit recognition. Pattern Recogn. 58, 172–189 (2016). https://linkinghub.elsevier.com/retrieve/pii/S0031320316300437
Sharif, S.M.A., Mohammed, N., Mansoor, N., Momen, S.: A hybrid deep model with HOG features for Bangla handwritten numeral classification. In: 2016 9th International Conference on Electrical and Computer Engineering (ICECE), pp. 463–466 (2016)
Smith, L.N.: Cyclical Learning Rates for Training Neural Networks. arXiv:1506.01186 [cs], June 2015
Smith, L.N.: A disciplined approach to neural network hyper-parameters: Part 1 - learning rate, batch size, momentum, and weight decay. arXiv:1803.09820 [cs, stat], March 2018
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014). http://jmlr.org/papers/v15/srivastava14a.html
Wen, Y., Lu, Y., Shi, P.: Handwritten Bangla numeral recognition system and its application to postal automation. Pattern Recogn. 40(1), 99–107 (2007). https://doi.org/10.1016/j.patcog.2006.07.001
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Chatterjee, S., Dutta, R.K., Ganguly, D., Chatterjee, K., Roy, S. (2020). Bengali Handwritten Character Classification Using Transfer Learning on Deep Convolutional Network. In: Tiwary, U., Chaudhury, S. (eds) Intelligent Human Computer Interaction. IHCI 2019. Lecture Notes in Computer Science(), vol 11886. Springer, Cham. https://doi.org/10.1007/978-3-030-44689-5_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-44689-5_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-44688-8
Online ISBN: 978-3-030-44689-5
eBook Packages: Computer ScienceComputer Science (R0)