Abstract
The process of attaching a symbolic identification to a character’s visual is known as character recognition. There are numerous handwritten characters of various languages, Bengali is one of them. Detecting handwritten documents is exceedingly challenging in today’s digital age due to the vast range of uses, unique shapes, and morphologically complicated formation. Besides, people’s handwritings are identical to them and vary according to sizes, shapes, and styles. Bangla has a lot of similar-looking characters that can be confusing to anyone who is not familiar with the language. In many circumstances, a single dot or mark distinguishes one character from another. Our paper describes an approach to recognize Bangla handwritten characters based on convolutional neural network. Here, we develop a new convolutional neural network model and test our model with CMATERdb 3.1.2 dataset. Our model obtains an average training accuracy of 98.78%, average validation accuracy of 98.33%, and average test accuracy of 98.21% on the alphabets of the dataset which outperforms the performances with the existing methods in the literature. This study paves the way for further advancements in the field of Bangla handwriting recognition by offering a framework for individual character recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Hasan MN, Sultan RI, Kasedullah M (2021) An automated system for recognizing isolated handwritten Bangla characters using deep convolutional neural network. In: 2021 IEEE 11th IEEE symposium on computer applications & industrial electronics (ISCAIE). IEEE, pp 13–18
Ahmed MS, Gonçalves T, Sarwar H (2016) Improving Bangla OCR output through correction algorithms. In: 2016 10th International conference on software, knowledge, information management & applications (SKIMA). IEEE, pp 338–343
Alom MZ, Sidike P, Taha TM, Asari VK (2017) Handwritten Bangla digit recognition using deep learning. arXiv preprint. arXiv:1705.02680
Bhattacharya U, Shridhar M, Parui SK, Sen PK, Chaudhuri BB (2012) Offline recognition of handwritten Bangla characters: an efficient two-stage approach. Pattern Anal Appl 15(4):445–458
Banerjee P, Chaudhuri BB (2013) An approach for Bangla and Devanagari video text recognition. In: Proceedings of the 4th international workshop on multilingual OCR, pp 1–5
Purkaystha B, Datta T, Islam MS (2017) Bengali handwritten character recognition using deep convolutional neural network. In: 2017 20th International conference of computer and information technology (ICCIT). IEEE, pp 1–5
Chowdhury AA, Ahmed E, Ahmed S, Hossain S, Rahman CM (2002) Optical character recognition of Bangla characters using neural network: a better approach. In: 2nd ICEE
Hasan MM, Abir MM, Ibrahim M, Sayem M, Abdullah S (2019) AIBangla: a benchmark dataset for isolated Bangla handwritten basic and compound character recognition. In: 2019 International conference on Bangla speech and language processing (ICBSLP). IEEE, pp 1–6
Chowdhury S, Wasee FR, Islam MS, Zaman HU (2018) Bengali handwriting recognition and conversion to editable text. In: 2018 Second international conference on advances in electronics, computers and communications (ICAECC). IEEE, pp 1–6
Rabby ASA, Haque S, Abujar S, Hossain SA (2018) Ekushnet: using convolutional neural network for Bangla handwritten recognition. Procedia Comput Sci 143:603–610
Rahman MM, Akhand MAH, Islam S, Shill PC, Rahman MH (2015) Bangla handwritten character recognition using convolutional neural network. Int J Image Graph Signal Process 7(8):42
Abir BM, Mahal SN, Islam MS, Chakrabarty A (2019) Bangla handwritten character recognition with multilayer convolutional neural network. In: Advances in data and information sciences. Springer, Singapore, pp 155–165
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Halder, M., Kundu, S., Hasan, M.F. (2023). An Improved Method to Recognize Bengali Handwritten Characters Using CNN. In: Saraswat, M., Chowdhury, C., Kumar Mandal, C., Gandomi, A.H. (eds) Proceedings of International Conference on Data Science and Applications. Lecture Notes in Networks and Systems, vol 552. Springer, Singapore. https://doi.org/10.1007/978-981-19-6634-7_43
Download citation
DOI: https://doi.org/10.1007/978-981-19-6634-7_43
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-6633-0
Online ISBN: 978-981-19-6634-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)