Ranjana Script Handwritten Character Recognition using CNN

Jen Bati - Kathmandu University, Dhulikhel, Kavre, 45210, Nepal
Pankaj Raj Dawadi - Kathmandu University, Dhulikhel, Kavre, 45210, Nepal

Citation Format:

DOI: http://dx.doi.org/10.30630/joiv.7.3.1725


This paper proposes a public image database for Ranjana script Handwritten Character Datasets (RHCD), publicly available for Ranjana script researchers or anyone interested in the subject. To the best of our knowledge, the Ranjana script Handwritten Character Dataset (RHCD) is the first publicly available database for Ranjana script researchers. Ranjana script descended from the Brahmi script, consists of 36 consonant letters, 16 vowel letters, and 10 numerical letters. The focus of this research is three-fold: the first is to create a new database for Ranjana script Handwritten Character Recognition; the second is to test the character recognition accuracy of the created RHCD using existing CNN algorithms like LeNET-5, AlexNET, and ZFNET algorithm; the third is to propose a model by investigating different hyper-tuning parameters to improve the recognition accuracy of the created RHCD. The research method applied in this study is dataset collection, digitization & cropping, pre-processing, dataset splitting, data augmentation, and finally, implementing the CNN model (existing and proposed). Performance evaluation is based on the test accuracy, precision, recall, and F1-score. The experiment result shows that our model ranks first, with a testing accuracy of 99.73% for 64x64 pixels resolution with precision, recall, and F1-score value 1. Creation and recognition of Ranjana script characters, vowel modifiers, and compound characters can be the next milestone to be achieved. Segmentation of words and sentences into characters and recognizing each character individually can be the next research domain.


Ranjana script; Newari script; RHCD; hyper-parameter; handwritten characters

Full Text:



E. R. Acharya, “Ranjana Numeral System: A Brief Information,†Journal of the Institute of Engineering, vol. 13, no. 1, pp. 221–224, Jun. 2017, doi: 10.3126/JIE.V13I1.20370.

Jens-Uwe and Hartmann, “The Ranjana Script,†1998, Accessed: May 11, 2023. [Online]. Available: https://epub.ub.uni-muenchen.de/25506/1/Hartmann_Ranjana_Script.pdf

R. Mohapatra, T. Mishra, … S. P.-2015 F. N., and undefined 2015, “OHCS: A database for handwritten atomic Odia Character Recognition,†ieeexplore.ieee.org, Accessed: May 11, 2023. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/7490020/

A. Elsawy, M. Loey, H. M. El-Bakry, A. El-Sawy, and H. El-Bakry, “Arabic handwritten characters recognition using convolutional neural network,†researchgate.net, Accessed: May 11, 2023. [Online]. Available: https://www.researchgate.net/profile/Hazem-El-Bakry/publication/313891953_Arabic_Handwritten_Characters_Recognition_using_Convolutional_Neural_Network/links/58ae09ef92851cf7ae85b2ce/Arabic-Handwritten-Characters-Recognition-using-Convolutional-Neural-Network.pdf

A. Ali, S. M.-J. of K. S. U.-C. and, and undefined 2022, “Intelligent handwritten recognition using hybrid CNN architectures based-SVM classifier with dropout,†Elsevier, Accessed: May 11, 2023. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1319157821000148

V. J. Ali, J. J.-I. J. S. E. Res, and undefined 2018, “A convolutional neural network based approach for recognizing malayalam handwritten characters,†researchgate.net, vol. 9, 2018, Accessed: May 11, 2023. [Online]. Available: https://www.researchgate.net/profile/Jabir-Ali-5/publication/329775635_A_Convolutional_Neural_Network_based_Approach_for_Recognizing_Malayalam_Handwritten_Characters/links/5c1a2713458515a4c7e9083e/A-Convolutional-Neural-Network-based-Approach-for-Recognizing-Malayalam-Handwritten-Characters.pdf

K. Manjusha, M. Kumar, K. S.-E. S. and Technology, and undefined 2019, “On developing handwritten character image database for Malayalam language script,†Elsevier, Accessed: May 11, 2023. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2215098618301447

D. Hijam and S. Saharia, “On developing complete character set Meitei Mayek handwritten character database,†Visual Computer, vol. 38, no. 2, pp. 525–539, Feb. 2022, doi: 10.1007/S00371-020-02032-Y.

Y. A. Nanehkaran, J. Chen, S. Salimi, and D. Zhang, “A pragmatic convolutional bagging ensemble learning for recognition of Farsi handwritten digits,†Journal of Supercomputing, vol. 77, no. 11, pp. 13474–13493, Nov. 2021, doi: 10.1007/S11227-021-03822-4.

R. Kummari and C. Bhagvati, “UHTelHwCC: A Dataset for Telugu Off-line Handwritten Character Recognition,†Communications in Computer and Information Science, vol. 1576 CCIS, pp. 249–262, 2022, doi: 10.1007/978-3-031-07005-1_22.

K. Aarif, P. S.-I. A. & Soft, and undefined 2022, “Multi-Domain Deep Convolutional Neural Network for Ancient Urdu Text Recognition System.,†search.ebscohost.com, doi: 10.32604/iasc.2022.022805.

L. Niharmine, B. Outtaj, A. A.-I. J. of, and undefined 2022, “Tifinagh handwritten character recognition using optimized convolutional neural network,†researchgate.net, doi: 10.11591/ijece.v12i4.pp4164-4171.

A. Onuean, U. Buatoom, T. Charoenporn, T. K.-A. Sciences, and undefined 2022, “Burapha-TH: A Multi-Purpose Character, Digit, and Syllable Handwriting Dataset,†mdpi.com, Accessed: May 11, 2023. [Online]. Available: https://www.mdpi.com/2076-3417/12/8/4083

A. Sharma, H. Bhardwaj, … A. B.-C., and undefined 2022, “A Machine Learning and Deep Learning Approach for Recognizing Handwritten Digits,†hindawi.com, Accessed: May 11, 2023. [Online]. Available: https://www.hindawi.com/journals/cin/2022/9869948/

S. Acharya, A. Pant, P. G.-2015 9th International, and undefined 2015, “Deep learning based large scale handwritten Devanagari character recognition,†ieeexplore.ieee.org, doi: 10.1109/SKIMA.2015.7400041.

M. Avadesh, N. G.-2018 13th I. I. Workshop, and undefined 2018, “Optical character recognition for Sanskrit using convolution neural networks,†ieeexplore.ieee.org, Accessed: May 11, 2023. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/8395237/

D. Chaudhary, K. S.-2019 6th I. Conference, and undefined 2019, “Hindi Handwritten Character Recognition using Deep Convolution Neural Network,†ieeexplore.ieee.org, Accessed: May 11, 2023. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/8991403/

B. Dessai, A. P.-2019 2nd I. C. on, and undefined 2019, “A deep learning approach for optical character recognition of handwritten Devanagari script,†ieeexplore.ieee.org, Accessed: May 11, 2023. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/8993342/

N. Aneja, S. Aneja, U. B. Darussalam, and B. Darussalam, “Transfer learning using CNN for handwritten devanagari character recognition,†ieeexplore.ieee.org, Accessed: May 11, 2023. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/8987286/

A. Ghimire, A. Chapagain, … U. B.-… R. J. of, and undefined 2020, “Nepali Handwriting Recognition using Convolution Neural Network,†search.proquest.com, Accessed: May 11, 2023. [Online]. Available: https://search.proquest.com/openview/fa91b4016f56904e9788f99b5947bfe4/1?pq-origsite=gscholar&cbl=5314840

Y. Gurav, P. Bhagat, … R. J.-… C. on E., and undefined 2020, “Devanagari handwritten character recognition using convolutional neural networks,†ieeexplore.ieee.org, Accessed: May 11, 2023. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9179193/

J. Sachdeva and S. Mittal, “Handwritten Offline Devanagari Compound Character Recognition Using CNN,†Lecture Notes on Data Engineering and Communications Technologies, vol. 90, pp. 211–220, 2022, doi: 10.1007/978-981-16-6289-8_18.

M. Kumar, S. Narang, M. K. Jindal, S. Rani Narang, and M. Tools, “DeepNetDevanagari: a deep learning model for Devanagari ancient character recognition,†Springer, vol. 80, no. 13, pp. 20671–20686, May 2021, doi: 10.1007/s11042-021-10775-6.

I. Dokare, S. Gadge, K. Kharde, … S. B.-2021 3rd I., and undefined 2021, “Recognition of Handwritten Devanagari Character using Convolutional Neural Network,†ieeexplore.ieee.org, 2021, doi: 10.1109/ICSPC51351.2021.9451716.

Y. LeCun, L. Bottou, … Y. B.-P. of the, and undefined 1998, “Gradient-based learning applied to document recognition,†ieeexplore.ieee.org, Accessed: May 11, 2023. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/726791/

A. Krizhevsky, I. Sutskever, G. H.-C. of the ACM, and undefined 2017, “Imagenet classification with deep convolutional neural networks,†dl.acm.org, vol. 60, no. 6, pp. 84–90, Jun. 2017, doi: 10.1145/3065386.

M. Zeiler, R. F.-C. V. 2014: 13th European, and undefined 2014, “Visualizing and understanding convolutional networks,†Springer, 2014, Accessed: May 11, 2023. [Online]. Available: https://link.springer.com/chapter/10.1007/978-3-319-10590-1_53

K. Simonyan, A. Z. preprint arXiv:1409.1556, and undefined 2014, “Very deep convolutional networks for large-scale image recognition,†arxiv.org, 2015, Accessed: May 11, 2023. [Online]. Available: https://arxiv.org/abs/1409.1556

C. Szegedy et al., “Going deeper with convolutions,†cv-foundation.org, Accessed: May 11, 2023. [Online]. Available: https://www.cv-foundation.org/openaccess/content_cvpr_2015/html/Szegedy_Going_Deeper_With_2015_CVPR_paper.html

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition.†pp. 770–778, 2016. Accessed: May 11, 2023. [Online]. Available: http://image-net.org/challenges/LSVRC/2015/