TamilSTARNet: segmentation via tri-phase architecture and attention-based recognition for handwritten Tamil characters
Source abstract
Abstract
Handwriting recognition plays a significant role in preserving cultural heritage, specifically in the context of ancient languages such as Tamil. Traditional Optical Character Recognition (OCR) systems find it challenging to handle these issues and hence report very low accuracies. To address the recognition of the complex structure of Tamil alphabets, this paper presents TamilSTARNet, an improved framework for handwritten Tamil document recognition. The proposed methodology consists of two main stages: (1) a three-stage segmentation process that segments. Tamil handwriting in a document into sentences, words, and characters despite its irregular spacing and intricate layouts and (2) an attention-driven recognition model with the view to enhance accuracy. The performance of the proposed model is evaluated using the uTHCD (90,000+ character samples spanning 156 classes) and HP Labs Offline Tamil (20,000+ handwritten words) datasets. The results show that the proposed model achieves an accuracy of 96.18%, proving its effectiveness in recognizing the intricate structure.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Handwritten Text Recognition Techniques · Advanced Neural Network Applications · Image Retrieval and Classification Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (25)
Show source-provided references
1. Jayanthi, V. & Thenmalar, S. A review on recognizing offline Tamil manuscript character. AIP Conf. Proc. 2591, 010001 (2023).10.1063/5.0120410 ↗
2. Antony Robert Raj, M., Abirami, S. & Shyni, S. M. Tamil handwritten character recognition system using statistical algorithmic approaches. Comput. Speech Lang. 78, 101448 (2023).10.1016/j.csl.2022.101448 ↗
3. Vinotheni, C. & Lakshmana Pandian, S. End-to-end deep-learning-based Tamil handwritten document recognition and classification model. IEEE Access 11, 43195–43204 (2023).10.1109/ACCESS.2023.3270895 ↗
4. Jayanthi, V. & Thenmalar, S. Recognition of Tamil handwritten text from a digital writing pad using MWDCNN. Multimed. Tools Appl. 83, 30261–30276 (2024).10.1007/s11042-023-16878-6 ↗
5. Dhivyaa, C. R. et al. Fine-Tuned Convolutional Neural Networks for Tamil Handwritten Text Recognition. In 2023 8th International Conference on Communication and Electronics Systems (ICCES) 450–456 (IEEE, 2023).10.1109/ICCES57224.2023.10192712 ↗
6. Memon, J. et al. Handwritten optical character recognition (OCR): a comprehensive systematic literature review (SLR). IEEE Access 8, 142642–142668 (2020).10.1109/ACCESS.2020.3012542 ↗
7. Lincy Babitha, R. et al. Handwritten Character Recognition System using Deep Learning Models for Tamil Language. In 2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS) 1120–1126 (IEEE, 2023).
8. Kavitha, B. R. & Srimathi, C. B. Benchmarking on offline Handwritten Tamil Character Recognition using convolutional neural networks. J. King Saud. Univ. Comput. Inf. Sci. 34.4, 1183–1190 (2022).10.1016/j.jksuci.2019.06.004 ↗
9. Shyni, S. M., Raj, M. A. R., & Abirami, S. Offline Tamil handwritten character recognition using sub line direction and bounding box techniques. Indian J. Sci. Technol. 8, 110–116 (2015).10.17485/ijst/2015/v8iS7/67780 ↗
10. Robert Raj Antony, M. & Abirami, S. Offline tamil handwritten character recognition using statistical based quad tree. Aust. J. Basic Appl. Sci. 10, 103–109 (2016).
11. Subramani, K. & Murugavalli, S. Recognizing ancient characters from Tamil palm leaf manuscripts using convolution based deep learning. Int. J. Recent Technol. Eng. 8, 6873–6880 (2019).
12. Manigandan, T. V. V. D. V. N. B. et al. Tamil character recognition from ancient epigraphical inscription using OCR and NLP. In 2017 International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS) 1850–1855 (IEEE, 2017).10.1109/ICECDS.2017.8389589 ↗
13. Vijay, A. et al. Transfer learning based offline handwritten recognition system using Tamil characters. In 2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS) 740–745 (IEEE, 2022).10.1109/ICSCDS53736.2022.9760893 ↗
14. Banavatu, T. & Parthasarathy, G. An effective handwritten character recognition framework for South Indian languages using adaptive deep learning network. Int. J. Image Graph. 2750008 (2024).10.1142/S0219467827500082 ↗
15. Karthikeyan, S. et al. Self-adaptive hybridized lion optimization algorithm with transfer learning for ancient Tamil character recognition in stone inscriptions. IEEE Access 11, 39621–39634 (2023).10.1109/ACCESS.2023.3268545 ↗
16. Shanmugam, K. & Vanathi, B. Newton algorithm based DELM for enhancing offline tamil handwritten character recognition. Int. J. Pattern Recognit. Artif. Intell. 36, 2250020 (2022).10.1142/S0218001422500203 ↗
17. Karthick, B., Singh, H. & Malarvel, M. Pre-processing techniques for offline tamil handwritten character recognition. In 2022 7th International Conference on Communication and Electronics Systems (ICCES) 976–981 (IEEE, 2022).10.1109/ICCES54183.2022.9835777 ↗
18. Lincy Babitha, R. & Gayathri, R. Optimized convolutional neural network for Tamil handwritten character recognition. Int. J. Pattern Recognit. Artif. Intell. 36, 2253003 (2022).10.1142/S0218001422530032 ↗
19. Woo, S., Park, J., Lee, J.-Y. & Kweon, I. S. CBAM: Convolutional block attention module. In Proc. European Conference on Computer Vision (ECCV) 3–19 (2018).10.1007/978-3-030-01234-2_1 ↗
20. Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017).
21. Wang, X. et al. Non-local neural networks. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 7794–7803 (2018).10.1109/CVPR.2018.00813 ↗
22. Shaffi, N. & Hajamohideen, F. uTHCD: a new benchmarking for Tamil handwritten OCR. IEEE Access 9, 101469–101493 (2021).10.1109/ACCESS.2021.3096823 ↗
23. Rajan, P. & Sridhar, S. Identification of ancient Tamil letters and its characters: Automatic date fixation based on contour-let technique. in Proc. 1st International Conference on Graphics and Signal Processing 40–43 (2017).10.1145/3121360.3121384 ↗
24. Kowsalya, S. & Periasamy, P. S. Recognition of Tamil handwritten character using modified neural network with aid of elephant herding optimization. Multimed. Tools Appl. 78, 25043–25061 (2019).10.1007/s11042-019-7624-2 ↗
25. Lincy Babitha, R. & Gayathri, R. Optimally configured convolutional neural network for Tamil Handwritten Character Recognition by improved lion optimization model. Multimed. Tools Appl. 80, 5917–5943 (2021).10.1007/s11042-020-09771-z ↗