Abstract
Optical Character Recognition (OCR) is at the forefront of numerous applications such as digitalization of legal and legacy documents, automatic form processing, writer identification in forensic intelligence. Most of these applications seldom have sufficient training samples in order to achieve an accuracy worthy of real-time deployments. Inspired by the demonstrated performance of Siamese Neural Networks (SNN) in various fields such as Computer vision, Natural Language Processing, Signal processing etc., in this paper, we explore the application of SNN for Tamil Handwritten character recognition. The Siamese-CNN learning is implemented using cross-entropy loss and subsequently used to validate the few-shot learning. It achieved an optimal accuracy of 83.39% for n-way-40-shot learning. Rigorous experiments were conducted all through and the results are indicative of a promising new direction for the development of efficient Indic OCR models using Siamese networks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Adak, C., Marinai, S., Chaudhuri, B.B., Blumenstein, M.: Offline Bengali writer verification by PDF-CNN and Siamese net. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 381–386. IEEE (2018)
Barakat, B.K., Alasam, R., El-Sana, J.: Word spotting using convolutional Siamese network. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 229–234. IEEE (2018)
Cao, Y., Ji, H., Zhang, W., Xue, F.: Visual tracking via dynamic weighting with pyramid-redetection based Siamese networks. J. Vis. Commun. Image Represent. 65, 102635 (2019)
Chaudhuri, U., Banerjee, B., Bhattacharya, A.: Siamese graph convolutional network for content based remote sensing image retrieval. Comput. Vis. Image Underst. 184, 22–30 (2019)
Hosseini-Asl, E., Guha, A.: Similarity-based text recognition by deeply supervised Siamese network. ar**v preprint ar**v:1511.04397 (2015)
Kornblith, S., Shlens, J., Le, Q.V.: Do better imagenet models transfer better? In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2661–2671 (2019)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 25, 1097–1105 (2012)
de Oliveira, I.O., Fonseca, K.V., Minetto, R.: A two-stream Siamese neural network for vehicle re-identification by using non-overlap** cameras. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 669–673. IEEE (2019)
Shaffi, N., Hajamohideen, F.: uTHCD: a new benchmarking for Tamil handwritten OCR. ar**v preprint ar**v:2103.07676 (2021)
Sharma, R., Kaushik, B.: Offline recognition of handwritten Indic scripts: a state-of-the-art survey and future perspectives. Comput. Sci. Rev. 38, 100302 (2020)
Sheng, W., Li, X.: Siamese denoising autoencoders for joints trajectories reconstruction and robust gait recognition. Neurocomputing 395, 86–94 (2020)
Strang, G.: Linear Algebra and Learning from Data. Wellesley-Cambridge Press, Cambridge (2019)
Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701–1708 (2014)
Wang, J., Liu, W., **ng, W., Wang, L., Zhang, S.: Attention shake Siamese network with auxiliary relocation branch for visual object tracking. Neurocomputing 400, 53–72 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Shaffi, N., Hajamohideen, F. (2021). Few-Shot Learning for Tamil Handwritten Character Recognition Using Deep Siamese Convolutional Neural Network. In: Mahmud, M., Kaiser, M.S., Kasabov, N., Iftekharuddin, K., Zhong, N. (eds) Applied Intelligence and Informatics. AII 2021. Communications in Computer and Information Science, vol 1435. Springer, Cham. https://doi.org/10.1007/978-3-030-82269-9_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-82269-9_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-82268-2
Online ISBN: 978-3-030-82269-9
eBook Packages: Computer ScienceComputer Science (R0)