Abstract
In this article, we study recognition of handwritten Assamese alphabet when Convolutional Neural Networks (CNN) are applied. First, we generate a dataset, consisting of the 52 characters, with over 12k images in total. To this dataset we apply LeNet-5, ResNet-50, InceptionV3, and DenseNet-201 models. Transfer learning is used for faster training. Best accuracy of over 94.62% is obtained on the test data. This is, currently, state of the art performance in Assamese character recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
This dataset is available from: Srinivasan Natesan at natesan@iitg.ac.in.
- 2.
Available from the UCI Machine Learning repository [5].
References
Al Rabbani Alif M, Ahmed S, Hasan MA (2017) Isolated Bangla handwritten character recognition with convolutional neural network. In: International conference on computer and information technology, Dhaka, Bangladesh, pp 1–6. https://doi.org/10.1109/ICCITECHN.2017.8281823
Aneja N, Aneja S (2019) Transfer learning using CNN for handwritten Devanagari character recognition. In: International conference on advances in information technology, Chikmagalur, India, pp 293–296
Bania RK, Khan R (2018) Handwritten Assamese character recognition using texture and diagonal orientation features with artificial neural network. Int J Appl Eng Res 13. https://doi.org/10.1007/978-981-15-0339-9
Baruah U, Hazarika SM (2015) A dataset of online handwritten Assamese characters. J Inf Process Syst 11:325–341. https://doi.org/10.3745/JIPS.02.0008.
Dua D, Graff C (2019) UCI machine learning repository Irvine. University of California, School of Information and Computer Science, CA
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. CVPR. Honolulu, HI, USA, pp 2261–2269
Jindal U, Gupta S, Jain V, Paprzycki M (2020) Offline handwritten Gurumukhi character recognition system using deep learning. Advances in intelligent systems and computing, vol 1064
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324. https://doi.org/10.1109/5.726791
Nair PP, James A, Saravanan C (2017) Malayalam handwritten character recognition using convolutional neural network. In: International conference on inventive communication and computational technologies, Coimbatore
Sarma P, Chourasia CK, Barman M (2019) Handwritten Assamese character recognition. In: IEEE conference for intelligent technologies, Bombay. India. https://doi.org/10.1109/ICAIT47043.2019.8987286
Singh H, Sharma RK, Singh VP (2021) Online handwriting recognition systems for Indic and non-Indic scripts: a review. Artif Intell Rev 54:1525–1579
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Conference on computer vision and pattern recognition (CVPR)
Wen J, Li S, Sun J (2013) A new binarization method for non-uniform illuminated document images. Pattern Recogn 46(6):1670–1690. https://doi.org/10.1016/j.patcog.2012.11.027
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yadav, M., Mangal, D., Natesan, S., Paprzycki, M., Ganzha, M. (2022). Assamese Character Recognition Using Convolutional Neural Networks. In: Mathur, G., Bundele, M., Lalwani, M., Paprzycki, M. (eds) Proceedings of 2nd International Conference on Artificial Intelligence: Advances and Applications. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-16-6332-1_70
Download citation
DOI: https://doi.org/10.1007/978-981-16-6332-1_70
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6331-4
Online ISBN: 978-981-16-6332-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)