Abstract
Tamil is one of the ancient Indian languages which has a vast collection of literature in the form of palm leaf, stones, metal plates, and other materials. Palm leaf manuscript was a broad tool to narrate medicines, literature, drama, and many more. Recognition of the characters written in palm leaf manuscripts is still an open task because of the need for digitization and transcription. In this paper, the recurrent neural network (RNN) is used to train the features of the characters extracted from the palm leaf. This method contains a preprocessing method to eliminate noise; then the character is segmented from the image and trained using the bidirectional long short-term memory (BLSTM) network. A feature vector with nine zones of character strokes is used to train and test the characters. A rich set of characters are used to train the features of the characters. This method provides better recognition accuracy than the other neural network-based character recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ko BC (2018) A brief review of facial emotion recognition based on visual information. Sensors 18(2):401
Graves A, Schmidhuber J (2005) Framewise phoneme classification with bidirectional lstm and other neural network architectures. Neural Netw 18(5):602–610
Kumar DU, Sreekumar G, Athvankar U (2009) Traditional writing system in southern India–palm leaf manuscripts. Des Thoughts 7:2–7
Shivachariar RV (2019) Agama academy. Online. Accessed 4 July 2019
Subashini (2017) Tamil heritage. http://thfcms.tamilheritage.org/category/palm-leaf/. Online. Accessed 4 July 2019
Noolaham Foundation (2015) Noolaham, http://www.noolaham.org/wiki/index.php/. Online. Accessed 4 July 2019
Ram Prashanth N, Siddarth B, Ganesh A, Kumar VN (2017) Handwritten recognition of Tamil vowels using deep learning. In: IOP conference series: materials science and engineering
Kiruba KB (2016) A survey of methods and strategies in Tamil palm script recognition. Int J Comput Sci Inf Technol 7(2):972–977
Panyam NS, TR VL, Krishnan R (2016) Modeling of palm leaf character recognition system using transform based techniques. Pattern Recogn Lett 84:29–34
Valy D, Verleysen M, Chhun S, Burie J (2018) Character and text recognition of khmer historical palm leaf manuscripts. In: 16th International conference on frontiers in handwriting recognition (ICFHR), pp 13–18
Vinoth YPR, Rajesh R (2017) Intelligence system for tamil vattezhuttu optical character recognition. Int J Comput Sci Eng Technol 8(04S):22–26
Shkarupa Y, Mencis R, Sabatelli M (2016) Offline handwriting recognition using LSTM recurrent neural networks. In: The 28th Benelux conference on artificial intelligence
Saxena LP (2014) An effective binarization method for readability improvement of stain-affected (degraded) palm leaf and other types of manuscripts. Curr Sci 107(3):489–496
Antara Kesiman MW, Burie JC, Ogier JM, Grangé P (2018) Knowledge representation and phonological rules for the automatic transliteration of balinese script on palm leaf manuscript. Computación y Sistemas 21
Chamchong R, Fung CC (2012) Text line extraction using adaptive partial projection for palm leaf manuscripts from Thailand. In: International conference on frontiers in handwriting recognition, pp 586–591
Gilloux M (2004) Hidden Markov models in handwriting recognition., In: Impedovo S (ed) Fundamentals in handwriting recognition. NATO ASI series (Series F: computer and systems sciences), vol 124
Chiang Y, Knoblock CA (2011) Recognition of multi-oriented, multi-sized, and curved text. In: International conference on document analysis and recognition, pp 1399–1403
Hafiz AM, Bhat GM (2014) Handwritten digit recognition using slope detail features. Int J Comput Appl 93:14–19
Hamrouni S, Cloppet F, Vincent N (2014) Handwritten and printed text separation: linearity and regularity assessment. In: Noise modelling in parallel magnetic resonance imaging: a variational approach, pp 387–394
Acknowledgements
Hereby the authors acknowledge Agama Academy for providing a rich set of digital archive of Tamil palm leaf manuscript for this research work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Athisayamani, S., Robert Singh, A., Sivanesh Kumar, A. (2021). Recurrent Neural Network-Based Character Recognition System for Tamil Palm Leaf Manuscript Using Stroke Zoning. In: Ranganathan, G., Chen, J., Rocha, Á. (eds) Inventive Communication and Computational Technologies. Lecture Notes in Networks and Systems, vol 145. Springer, Singapore. https://doi.org/10.1007/978-981-15-7345-3_14
Download citation
DOI: https://doi.org/10.1007/978-981-15-7345-3_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-7344-6
Online ISBN: 978-981-15-7345-3
eBook Packages: EngineeringEngineering (R0)