Handwritten Text Recognition Using Deep Learning: A CNN-LSTM Approach
Keywords:
Convolutional Neural Network, Long Short-Term Memory, Connectionist Temporal Classification, IAM Dataset, Optical Character Recognition.Abstract
Handwritten Text Recognition (HTR) has undergone major improvements due to the rise of deep learning. This research introduces a novel approach to hybrid Convolutional Neural Networks (CNNs) in conjunction with Long Short-Term Memory (LSTM) model for accurate recognition of handwritten text. The model is trained using the IAM dataset, consisting of 13,353 handwritten text lines and 115,320 words. The preprocessing pipeline includes grayscale conversion, normalization, and data augmentation to enhance generalization. The CNN is responsible for capturing spatial features from input images, while the LSTM captures sequential dependencies in text, followed by the CTC (Connectionist Temporal Classification) loss function is employed for alignment. Experimental results show an overall Character Error Rate (CER) of 4.57% and a Word Error Rate (WER) of 12.3%. The model outperforms traditional OCR methods and demonstrates robustness in recognizing cursive, printed, and mixed-script handwriting styles. This research highlights the potential of deep learning in real-world used in various applications, including digitizing historical documents, bank cheque processing, and automated postal services.
Downloads
References
S. S. Roy, S. Basu, and M. Nasipuri, “Handwritten Text Recognition Using Deep Learning: A ,” Pattern Recognition Letters, vol. 144, pp. 1-12, 2021.
C. Vinotheni and S. Lakshmanapandian, "End-to-End Deep-Learning-Based Tamil Handwritten Document Recognition and Classification Model," IEEE Access, vol. 11, pp. 45123-45135, Apr. 2023.
D. Coquenet, C. Chatelain, and T. Paquet, "End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 1, pp. 123-135, Jan. 2023.
S. Y. Manchala, J. Kinthali, K. Kotha, K. S. Kumar, and J. Jayalaxmi, "Handwritten Text Recognition Using Deep Learning with TensorFlow," Proceedings of Aditya Institute of Technology and Management, Srikakulam, Andhra Pradesh, 2023.
Y. Zhang and G. Li, "Improving Handwritten Mathematical Expression Recognition via Integrating Convolutional Neural Network With Transformer and Diffusion-Based Data Augmentation," IEEE Access, vol. 12, pp. 1–12, May 2024.
J. Shin, K. Hirooka, Y. Uchida, M. Maniruzzaman, A. Megumi, and A. Yasumura, "Online Handwriting-Based Gender Recognition Using Statistical and Machine Learning Approaches," IEEE Access, vol. 12, pp. 1–12, July 2024.
R. Malhotra and M. T. Addis, "End-to-End Historical Handwritten Ethiopic Text Recognition Using Deep Learning," IEEE Access, vol. 11, pp. 1–10, Sep. 2023.
A. Graves et al., “A Novel Connectionist System for Unconstrained Handwriting Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 5, pp. 855-868, 2023.
U.-V. Marti and H. Bunke, “The IAM-database: An English Sentence Database for Off-line Handwriting Recognition,” International Journal on Document Analysis and Recognition, vol. 5, no. 1, pp. 39-46, 2022.
A. H. Nisa, "A Deep Learning Approach to Handwritten Text Recognition In The Presence Of Struck-Out Text," in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013.
Andreu, "Handwritten Text Recognition for Bengali Language," in International Conference on Frontiers in Handwriting Recognition, 2013.
M. L. Saini, D. C. Sati, R. S. Telikicharla, and Mahadev, "Handwritten English script recognition system using CNN and LSTM," in Proc. IEEE Contemp. Comput. Commun. (InC4), Punjab, India, 2024.
K. He, "Handwritten Digit Recognition Based on Convolutional Neural Network," 2023 IEEE Electronic Technology, Communication and Information (ICETCI), Xi’an, China, 2023.
M. B. Subha, P. V. Ramanan, and V. K. T. Malini, "Offline Recognition of Handwritten Text Using Combination of Neural Networks," in Commun. Electron. Syst. (ICCES), Chennai, India, 2023.
P. Latchoumy, G. Kavitha, H. S. Banu, and S. Anupriya, "Handwriting Recognition Using Convolutional Neural Network and Support Vector Machine Algorithms," in Electron., Commun., Aerosp. Technol. (ICECA), Chennai, India, 2022.
B. Rajyagor and R. Rakhlia, "Handwritten Character Recognition using Deep Learning," Int. J. Recent Technol. Eng. (IJRTE), vol. 8, no.6,pp.1-3,Mar.2020.
S. Y. Manchala, K. Kinthali, K. Kotha, K. S. Kumar, and J. Jayalaxmi, "Handwritten Text Recognition using Deep Learning with TensorFlow," Int. J. Eng. Res. Technol. (IJERT), vol. 9, no. 5, pp. 2-3, May2020.
A. Ansari, A. Singh, B. Kaur, D. Singh, and M. Rakhra, "Handwritten Text Recognition using Deep Learning Algorithms," 2022 4th International Conference on Artificial Intelligence and Speech Technology (AIST), Phagwara, India, 2022.
S. S. Rajput and Y. Choi, "Handwritten digit recognition using convolution neural networks," in Proc. IEEE 12th Annu. Comput. Commun. Workshop Conf. (CCWC), Fullerton, CA, USA, 2022.
S. Chauhan, S. Mahmood, and T. Poongodi, "Handwritten digit recognition using deep neural networks," in Intell. Eng. Manag. (ICIEM), Greater Noida, India, 2023.
H. M. Balaha and H. A. Ali, "A new Arabic handwritten character recognition deep learning system (AHCR-DLS)," Neural Comput. Appl.,vol.33,pp.6325–6367,Oct.2020.
K. R. Shah and D. D. Badgujar, "Devnagari Handwritten Character Recognition (DHCR) for Ancient Documents: A Review," Proceedings of the 2013 IEEE Information and Communication Technologies (ICT 2013), Lonavala, India, 2023.
H. Bhardwaj, R. Das, P. Garg, and R. Kumar, "Handwritten Text Recognition Using Deep Learning," 2024 Intelligence CommunicationTechnologies(CCICT),Gurugram,India,2024.
D. Narynbayev, A. Serikkhan, A. Barkhandinova, and I. Mohammad, "Kazakh Handwritten Text Recognition Using Computer Vision and Neural Network,"Electronics Computer and Computation (ICECCO), Kaskelen, Kazakhstan,2023.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
