Authors : Subodh Kant; Dr. Gaurav Harit

Volume/Issue : Volume 11 - 2026, Issue 7 - July

Google Scholar : https://tinyurl.com/52wm8eau

Scribd : https://tinyurl.com/2kzrcpdk

DOI : https://doi.org/10.38124/ijisrt/26jul106

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : This survey presents a comprehensive synthesis of contemporary research in handwritten text recognition (HTR), encompassing bibliometric analysis, systematic methodological reviews, and novel architectural innovations spanning line-level, document-level, and multi-lingual recognition systems. Drawing from 25 original research works, survey papers, and empirical studies, this work categories existing literature into ten thematic clusters: survey and review studies, meta-learning and adaptation methods, self-supervised learning approaches, vision-language models, transformerbased architectures, word and keyword spotting methods, document-level recognition systems, low-resource and Indic script recognition, foundational deep learning architectures, and out-of-distribution generalization studies. The survey reveals that while significant progress has been achieved through deep learning and transfer learning techniques, critical challenges persist in handling domain shifts, low-resource languages, and complex document layouts. Furthermore, emerging paradigms including self-supervised vision transformers, meta-learning frameworks, and foundation models demonstrate substantial promise for enabling more adaptive, efficient, and generalisable HTR systems. This paper synthesises these developments, identifies cross-cutting methodological themes, analyses comparative performance trends, and delineates key research gaps that warrant future investigation.

Keywords : Handwritten Text Recognition, Deep Learning, Meta-Learning, Vision Transformers, Self-Supervised Learning, Domain Adaptation, Foundation Models, Indic Scripts.

References :

1. V. Agrawal, J. Jagtap, and M. V. V. Prasad Kantipudi, “Exploration of advancements in handwritten document recognition techniques,” Intelligent Systems with Applications, vol. 22, Art. no. 200346, 2024.
2. C. Garrido-Muñoz, A. Rios-Vila, and J. Calvo-Zaragoza, “Handwritten text recognition: A survey,” arXiv preprint arXiv:2502.08417, 2025.
3. A. K. Bhunia, S. Khan, A. Fischer, F. S. Khan, and L. Shao, “MetaHTR: Meta-learning for writer-adaptive handwritten text recognition,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 1581–1590.
4. W. Gu, L. Gu, Z. Wang, C. Y. Suen, and Y. Wang, “DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning,” arXiv preprint arXiv:2501.12898, 2025.
5. W. Gu, L. Gu, C. Y. Suen, and Y. Wang, “MetaWriter: Personalized handwritten text recognition using meta-learned prompt tuning,” arXiv preprint arXiv:2505.20513, 2025.
6. S. K. Jemni, M. E. Souibgui, Y. Kessentini, and A. Fornés, “ST-KeyS: Self-supervised transformer for keyword spotting in historical documents,” in Proc. Digital Humanities Conference, 2023.
7. F. Wolf and G. A. Fink, “Self-training of handwritten word recognition for synthetic-to-real adaptation,” in Proc. International Conference on Document Analysis and Recognition (ICDAR), 2019, pp. 1–8.
8. M. Caron, H. Touvron, I. Misra, H. Jégou, J. Mairal, P. Bojanowski, et al., “Emerging properties in self-supervised vision transformers,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 9650–9660.
9. M. Oquab, T. Darcet, T. Moutakanni, H. Vo, M. Szafraniec, V. Khalidov, et al., “DINOv2: Learning robust visual features without supervision,” arXiv preprint arXiv:2304.07193, 2023.
10. Y. H. M. Chung and D. Choi, “Finetuning vision-language models as OCR systems for low-resource languages: A case study of Manchu,” arXiv preprint arXiv:2507.06761, 2025.
11. A. Fadeeva, V. Coriou, D. Antognini, C. Musat, and A. Maksai, “InkFM: A foundational model for full-page online handwritten note understanding,” arXiv preprint arXiv:2503.23081, 2025.
12. A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, et al., “Learning transferable visual models from natural language supervision,” in Proc. International Conference on Machine Learning (ICML), 2021, pp. 8748–8763.
13. Y. Li, Y. Zhu, and Z. Lian, “HTR-VT: Handwritten text recognition with vision transformer,” arXiv preprint arXiv:2409.08573, 2024.
14. L. Kumari, P. Mazumdar, and P. Bhattacharyya, “GatedLexiconNet: End-to-end handwritten paragraph recognition,” arXiv preprint arXiv:2404.14062, 2024.
15. M. Hamdan, L. S. Saoud, and N. Houmani, “HTR-JAND: Joint attention network and knowledge distillation for handwritten text recognition,” arXiv preprint arXiv:2412.18524, 2024.
16. D. Coquenet, “Meta-DAN: Towards an efficient prediction strategy for page-level handwritten text recognition,” arXiv preprint arXiv:2504.03349, 2025.
17. B. V. Kasuba, M. K. Chinnakotla, and C. V. Jawahar, “PLATTER: Page-level recognition for Indic languages,” arXiv preprint arXiv:2502.06172, 2025.
18. L. Sharma, A. Bhatt, and N. Garg, “Advancements in handwritten Devanagari character recognition using deep learning,” Discover Applied Sciences, vol. 6, 2024.
19. K. V. C. Madhav, A. Veeramaneni, P. A. Sriya, K. Sumanth, J. C. Jyotsna, T. Singh, and P. Duraisamy, “Handwritten Devanagari numeral recognition using deep learning,” in Proc. 2024 3rd International Conference for Innovation in Technology (INOCON), Karnataka, India, Mar. 2024, pp. 1–6, doi: 10.1109/INOCON60754.2024.10511947.
20. C. Garrido-Muñoz and J. Calvo-Zaragoza, “On the generalization of handwritten text recognition models,” arXiv preprint arXiv:2411.17332, 2024.