A DHCR_SmartNet: A smart Devanagari Handwritten Character Recognition using Level-wised CNN Architecture



  • Shalaka P. Deore Department of Computer Science & Engineering, Sathyabama Institute of Science and Technology, Chennai, India




Handwritten Script Recognition is a vital application of Machine Learning domain. Applications like automatic number plate detection, pin code detection and managing historical documents increasing more attention towards handwritten script recognition. English is the most widely spoken language, hence there has been a lot of research into identifying a script using a machine. Devanagari is popular script used by a huge number of people in the Indian Subcontinent. In this paper, level-wised efficient transfer learning approach presented on VGG16 model of Convolutional Neural Network (CNN) for identification of Devanagari isolated handwritten characters. In this work a new dataset of Devanagari characters is presented and made accessible publicly. Newly created dataset comprises 5800 samples for 12 vowels, 36 consonants and 10 digits. Initially simple CNN is implemented and trained on this new small dataset. In next stage transfer learning approach is implemented on VGG16 model and in last stage fine-tuned efficient VGG16 model is implemented. The training and testing accuracy of fine-tuned model are obtained as 98.16% and 96.47% respectively.


Download data is not yet available.


Pal U. and Chaudhuri B. B.: Indian script character recognition: A survey. Pattern Recognition, vol. 37(9), pp. 1887–1899, 2004.

Ly N., Nguyen C., Nguyen K. and Nakagawa M.: Deep Convolutional Recurrent Network for Segmentation-Free Offline Handwritten Japanese Text Recognition. 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 5-9, 2017, doi: 10.1109/ICDAR.2017.357.

Wu Y.C., Yin F. and Liu C. L.: Improving handwritten Chinese text recognition using neural network language models and convolutional neural network shape models. Pattern Recognition, vol. 65, pp. 251-264, 2017.

Plamondon R. and Srihari S. N.: Online and off-line handwriting recognition: a comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22(1), pp. 63-84, 2000, doi: 10.1109/34.824821.

Jayadevan R., Kolhe S. R., Patil P. M. and Pal U.: Offline recognition of Devanagari script: A survey. IEEE Transactions on Systems, Man, and Cybernetics-part C: Applications and Reviews, vol. 41(6), pp. 782-796, 2011, doi: 10.1109/TSMCC.2010.2095841.

Sonkusare M., Gupta R. and Moghe A.: A Review on Character Segmentation Approach for Devanagari Script. Intelligent Systems, Springer, Singapore, pp. 181-189, 2021.

Kohli M. and Kumar S.: Segmentation of handwritten words into characters. Multimedia Tools and Applications, vol. 80(14), pp. 22121-22133, 2021, doi: https://doi.org/10.1007/s11042-021-10638-0.

Roy P., Bhunia A., Das A., Dey P. and Pal U.: HMM-based Indic handwritten word recognition using zone segmentation. Pattern Recognition, vol. 60, pp. 1057-1075, 2016, doi: https://doi.org/10.1016/j.patcog.2016.04.012

Bhunia A. K., Roy P. P., Mohta A. O. and Pal U.: Cross-language framework for word recognition and spotting of indic scripts. Pattern Recognition, vol. 79, pp.12-31, 2018, doi: https://doi.org/10.1016/j.patcog.2018.01.034

Islam N., Islam Z. and Noor N.: A Survey on Optical Character Recognition System. Journal of Information & Communication Technology-JICT, vol. 10 (2), pp. 1-4, 2016.

Ren X., Zhou Y., Huang Z., Sun J., Yang X. and Chen K.: A Novel Text Structure Feature Extractor for Chinese Scene Text Detection and Recognition. IEEE Access, vol. 5, pp. 3193-3204, 2017, doi: 10.1109/ACCESS.2017.2676158.

Jino P. J., Balakrishnan K. and Bhattacharya U.: Offline Handwritten Malayalam Word Recognition Using a Deep Architecture. In Soft Computing for Problem Solving, Advances in Intelligent Systems and Computing, ed. J. Bansal, K. Das, A. Nagar, K. Deep and A. Ojha, vol. 816, pp. 913-925. Singapore, Springer, 2019, doi: https://doi.org/10.1007/978-981-13-1592-3_73.

Narang S., Jindal M. K. and Kumar M.: Devanagari ancient documents recognition using statistical feature extraction techniques. Sādhanā, vol. 44(141), pp. 1-8, 2009, doi: https://doi.org/10.1007/s12046-019-1126-9.

Dutta K., Krishnan P., Mathew M. and. Jawahar C. V.: Towards accurate handwritten word recognition for Hindi and Bangla. In: Conference on Computer Vision, Pattern Recognition, Image Processing, and Graphics, Springer, Singapore, vol. 841, pp. 470-480, 2017, https://doi.org/10.1007/978-981-13-0020-2_4.

Bolan S. and Shijian L.: Accurate recognition of words in scenes without character segmentation using recurrent neural network. Pattern Recognition, vol. 63, pp. 397-405, 2017, doi :https://doi.org/10.1016/j.patcog.2016.10.016.

Lee H., Grosse R., Ranganath R. and Ng A. Y.: Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In Proceedings of the 26th Annual International Conference on Machine Learning, ACM, New York, NY, USA, pp. 609–616, 2009.

Liu W., Wang Z., Liu X., Zeng N., Liu Y. and Alsaadi F. E.: A survey of deep neural network architectures and their applications. Neurocomputing, vol. 234, pp.11-26, 2017, doi: https://doi.org/10.1016/j.neucom.2016.12.038.

Alom M. Z., Sidike P., Taha T. M. and Asari V. K.: Handwritten Bangla Character Recognition Using the State-of-the-Art Deep Convolutional Neural Networks. Computational Intelligence and Neuroscience, vol. 2018, pp.1-13, 2018, doi: https://doi.org/10.1155/2018/6747098.

Jangid M. and Srivastava S.: Handwritten Devanagari Character Recognition Using Layer-Wise Training of Deep Convolutional Neural Networks and Adaptive Gradient Methods. Journal of Imaging, vol. 4(2), pp. 1-14, 2018, doi: https://doi.org/10.3390/jimaging4020041.

He K., Zhang X., Ren S. and Sun J.: Deep residual learning for image recognition, 2015. In CVPR. arXiv:1512.03385[cs.CV].

Guha R., Das N., Kundu M., Nasipuri M. and Santosh K. C.: DevNet: An Efficient ture for Handwritten Devanagari Character Recognition. International Journal of Pattern Recognition and Artificial Intelligence, 2019, doi: https://doi.org/10.1142/S0218001420520096.

Obaidullah S.M., Halder C. and Santosh K.C.: PHDIndic_11: page-level handwritten document image dataset of 11 official Indic scripts for script identification. Multimedia Tools and Applications, vol. 77, pp. 1643–1678, 2018, doi: https://doi.org/10.1007/s11042-017-4373-y.

Santosh K.C. and Wendling L.: Character recognition based on non-linear multi-projection profiles measure. Frontiers of Computer Science, vol. 9, pp.678–690, 2015, doi: https://doi.org/10.1007/s11704-015-3400-2.

Xiao N. and Ching Y.: A novel hybrid CNN–SVM classifier for recognizing handwritten digits. Pattern Recognition, vol. 45(4), pp.1318-1325, 2012, doi: https://doi.org/10.1016/j.patcog.2011.09.021.

Younis K.: Arabic Handwritten Character Recognition Based On Deep Convolutional Neural Networks. Jordanian Journal of Computers and Information Technology (JJCIT), vol. 3 (3), pp.186-200, 2017.

Md. Mahbubar R., Akhand M. A. H., Islam S., Shill P. C. and Hafizur Md. R.: Bangla Handwritten Character Recognition using Convolutional Neural Network. International Journal of Image, Graphics and Signal Processing, vol. 8, pp. 52-59, 2015, doi: 10.5815/ijigsp.2015.08.06.

Simonyan K. and Zisserman A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. In CVPR, 2015. arXiv:1409.1556v6[cs.CV].

Russakovsky O., Deng J. and Su H.: Imagenet large scale visual recognition challenge. International Journal of Computer Vision, vol. 115, pp. 211–252, 2015, doi: https://doi.org/10.1007/s11263-015-0816-y.

Nair V. and Hinton G. E.: Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel, pp. 807–814, 2010.

Srivastava N., Hinton G., Krizhevsky A., Sutskever I. and Salakhutdinov R.: Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, vol. 15(56), pp. 1929–1958, 2014.

Acharya S., Pant A. and Gyawali P.: Deep Learning Based Large Scale Handwritten Devanagari Character Recognition. In Proceedings of the 9th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), pp. 121-126. Kathmandu, 2015, doi: 10.1109/SKIMA.2015.7400041.

Sarkhel R., Das N., Basu S., Kundu M. and Nasipuri M.: CMATERdb1 : a database of unconstrained handwritten Bangla and Bangla–English mixed script document image. International Journal on Document Analysis and Recognition, vol. 15, pp.71-83, 2012, doi: https://doi.org/10.1007/s10032-011-0148-6

Saha C., Faisal R. and Mostafijur R.: Bangla Handwritten Character Recognition Using Local Binary Pattern and Its Variants. In Proceeding of International Conference on Innovations in Science, Engineering and Technology, Chittagong, Bangladesh, pp. 236-241, 2018, doi: 10.1109/ICISET.2018.8745645.

Vijaya Kumar R. and Babu U.: Handwritten Hindi Character Recognition using Deep Learning Techniques. International Journal of Computer Sciences and Engineering, vol. 7(2), pp. 1-7, 2019, doi: 10.26438/ijcse/v7i2.17

Saha P. and Jaiswal A.: Handwriting Recognition Using Active Contour. In Proceeding of the Artificial Intelligence and Evolutionary Computations in Engineering Systems. Advances in Intelligent Systems and Computing, vol. 1056, Singapore. Springer, pp. 505-514, 2020, doi: https://doi.org/10.1007/978-981-15-0199-9_43.




How to Cite

Deore, S. P. (2022). A DHCR_SmartNet: A smart Devanagari Handwritten Character Recognition using Level-wised CNN Architecture: DHCR_SmartNet. Computer Science, 23(3), 303. https://doi.org/10.7494/csci.2022.23.3.4487