Deep learning based hand written character recognition for manuscript documents

Document Type : Research Paper


1 Faculty of Electronics Engineering, Sathyabama Institute of Science & Technology, IT Highway, Chennai, India

2 Principal, Swarnandhra College of Engineering & Technology, Narasapur, India

3 School of Electrical & Electronics, Sathyabama Institute of Science & Technology, Chennai, India


Handwritten manuscripts contain much ancient information related to astrology, medicines, grammar etc. They are of various forms such as palm leaves, paper, stones etc. These manuscripts are preserved by the method of digitization with noise introduced. By using proper filtering as well as denoising methods these noises are eliminated and the images are restored. It is finally required to recognize the handwritten characters automatically from the restored image enabling the researchers and enthusiasts for going through the document very easily. This proposed work deals with the creation of a handwritten characters dataset for all the characters within a specific dimensional area and the recognition of handwritten characters using the deep learning method. First, the handwritten dataset is created from different human handwritings in a specific format, scanned and each character with suitable dimension is obtained by labelling them as per the sequence. Then various forms of convolution network are applied for the character recognition and the results are compared to obtain the suitable net for the Tamil character recognition from the handwritten document.


[1] N. Aneja and S. Aneja, Transfer learning using CNN for handwritten devanagari character recognition, 1st Int.
Conf. Adv. Inf. Technol. Chikmagalur, India, (2019) 293–296.
[2] S. Anto, Supervised machine learning approaches for medical data set classification-A review, IJCST, 2(4) (2011)
[3] A. Anwar, Difference between AlexNet, VGGNet, ResNet and Inception, Medium, (2020).
[4] J. Brownlee, What is a confusion matrix in machine learning, Machine Learning Mastery, (2016).
[5] D. Ciresan and U. Meier, Multi-column deep neural networks for offline handwritten Chinese character classification, International Joint Conference on Neural Networks (IJCNN), Killarney, Ireland, (2015) 1–6.
[6] P. Chansung, CIFAR-10 image classification in TensorFlow, Medium, (2018).
[7] Dataset – department of computer science,, 2020.
[8] Data sets of printed Tamil characters and printed documents, University of Jaffna,, Apr. 19, 2016.
[9] S.P. Deore and A. Pravin, Devanagari handwritten character recognition using fine-tuned deep convolutional
neural network on trivial dataset, S¯adhan¯a, 45(1) 243.
[10] K. He, X. Zhang, S. Ren and J. Sun, Deep residual learning for image recognition, IEEE Conference on Computer
Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, (2016) 770–778.[11] A. Krizhevsky and G. Hinton, Learning multiple layers of features from tiny images, University of Toronto, 2009.
[12] A. Krizhevsky, I. Sutskever and G.E. Hinton, ImageNet classification with deep convolutional neural networks,
Commun. ACM 60(6) (2017) 84–90.
[13] L. Likforman-Sulem and E. Kavallieratou, Document image processing, J. Imag. 4(7) (2018) 84.
[14] A.H. Mawaddah, C.A. Sari, D.R.I. Moses Setiadi and E.H. Rachmawanto, Handwriting recognition of hiragana
characters using convolutional neural network, International Seminar on Application for Technology of Information and Communication (iSemantic), Semarang, Indonesia, (2020) 79–82.
[15] M.A. Muthiah, E. Logashanmugam, N.M. Nandhitha, C.K. Kumar and D. Hariteja, Performance evaluation of
conventional CNN architectures and modified ALEXNET for the classification of potatoes by thermal imaging,
Russ. J. Nondestruct Test 56(9) (2020) 718–726.
[16] K. Muthuvel and S.L. Padma, Hybrid features and classifier for classification of ECG signal, RJASET, 9(12)
(2015) 1034–1050.
[17] J. Patterson and A. Gibson, Deep Learning: A Practitioner’s Approach, O’Reilly Media, Inc., 2017.
[18] M.A. Pragathi, K. Priyadarshini, S. Saveetha, A.S. Banu and K.O.M. Aarif, Handwritten Tamil character recognition using deep learning, International Conference on Vision Towards Emerging Trends in Communication and
Networking (ViTECoN), Vellore, India, (2019) 1–5.
[19] M. Ramanan, A. Ramanan and E.Y.A. Charles, A preprocessing method for printed Tamil documents: Skew
correction and textual classification, IEEE Seventh International Conference on Intelligent Computing and Information Systems (ICICIS), Cairo, Abbassia, Egypt, (2015) 495–500.
[20] J. Schmidhuber, Deep learning in neural networks: An overview, Neural Networks 61 (2015) 85–117.
[21] B. Sen and V. Vedanarayanan, Efficient classification of breast lesion based on deep learning technique, BIJAIP
6(1) (2016) 01–06.
[22] R. Sharma and B. Kaushik, Offline recognition of handwritten Indic scripts: A state-of-the-art survey and future
perspectives, Comput. Sci. Rev. 38 (2020) 100302.
[23] K. Subramani and M. Subramaniam, Creation of original Tamil character dataset through segregation of ancient
palm leaf manuscripts in medicine, Expert Syst. 38(1) (2020).
[24] Tamil Character Classification,, 2020.
[25] K. Younis and A. Khateeb, Arabic hand-written character recognition based on deep convolutional neural networks,
JJCIT 3(3) (2017) 186.
Volume 12, Special Issue
December 2021
Pages 1439-1447
  • Receive Date: 12 August 2021
  • Revise Date: 08 September 2021
  • Accept Date: 03 November 2021