Challenges and Opportunities in Brahmi Script Recognition using Artificial Intelligence
Keywords:
artificial intelligence, Brahmi script, culture, deep learning, heritage, Indian languages, OCR, stone inscriptionsAbstract
This study presents a comprehensive analysis of OCR systems specifically designed for stone inscriptions in various ancient languages. It focuses on the techniques, challenges, and advancements related to digitizing and preserving ancient texts engraved on stone. The unique characteristics of stone inscriptions, including diverse languages, ancient scripts, erosion, weathering, and non-uniform lighting conditions, are discussed. Techniques for image enhancement, feature extraction, and recognition models are investigated, with a specific emphasis on handling complexities like the Brahmi script. The research examines challenges associated with segmentation, character recognition, and the incorporation of linguistic and historical knowledge. Existing OCR frameworks, evaluation metrics, and recent advancements, such as machine learning, deep learning, and advanced imaging technologies, are presented. This study serves as a valuable resource for researchers and professionals involved in deciphering and preserving ancient stone inscriptions. It identifies opportunities for developing innovative artificial intelligence methods to enhance Brahmi script recognition for stone inscriptions, aiming to achieve better performance and improved accuracy. Promising results have not yet been achieved for OCR systems for various ancient scripts, even though several techniques have been developed So, it is possible to incorporate novel algorithmic techniques of artificial intelligence as well as suitable parameters to gain efficiency and accuracy in existing algorithms.
Downloads
References
Devi, H.K.A., 2006. Thresholding: A Pixel-Level Image Processing Methodology Preprocessing Technique for an OCR System for the Brahmi Script. Ancient Asia, 1(0), p.161-165.DOI: https://doi.org/10.5334/aa.06113
Dammi Bandara1, Nalin Warnajith, Atsushi Minato and Satoru Ozawa, "Creation of precise alphabet fonts of early Brahmi script from photographic data of ancient Sri Lankan inscriptions", Canadian Journal on Artificial Intelligence, Machine Learning and Pattern Recognition Vol. 3 No. 3, May 2012
Gautam, N., Sharma, R.S., Hazrati, G. (2016). Handwriting Recognition of Brahmi Script (an Artefact): Base of PALI Language. In: Satapathy, S., Das, S. (eds) Proceedings of First International Conference on Information and Communication Technology for Intelligent Systems: Volume 2. Smart Innovation, Systems and Technologies, vol 51. Springer, Cham. https://doi.org/10.1007/978-3-319-30927-9_51
T. S. Suganya and S. Murugavalli, "Feature selection for an automated ancient Tamil script classification system using machine learning techniques," 2017 International Conference on Algorithms, Methodology, Models and Applications in Emerging Technologies (ICAMMAET), Chennai, India, 2017, pp. 1-6, doi: 10.1109/ICAMMAET.2017.8186731.
[5] Jyothi R. L. and Abdul Rahiman M., "Comparative Analysis of Wavelet Transforms in the Recognition of Ancient Grantha Script", International Journal of Computer Theory and Engineering, Vol. 9, No. 4, August 2017
Gautam, Neha & Chai, Soo See. (2017). Optical Character Recognition for Brahmi Script Using Geometric Method.
V. Romero, J. A. Sánchez and A. H. Toselli, "Active Learning in Handwritten Text Recognition using the Derivational Entropy," 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), Niagara Falls, NY, USA, 2018, pp. 291-296, doi: 10.1109/ICFHR-2018.2018.00058.
S. Al-Maadeed, S. F. K. Peer and N. Subramanian, "Data Collection and Image Processing System for Ancient Arabic Manuscripts," 2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR), London, UK, 2018, pp. 124-128, doi: 10.1109/ASAR.2018.8480251.
Shruti Daggumati, Peter Z. Revesz, "Data Mining Ancient Script Image Data Using Convolutional Neural Networks", IDEAS '18: Proceedings of the 22nd International Database Engineering & Applications Symposium, June 2018, Pages 267–272, doi: 10.1145/3216122.3216163
S. R. Narang, M. K. Jindal and P. Sharma, "Devanagari Ancient Character Recognition using HOG and DCT Features," 2018 Fifth International Conference on Parallel, Distributed and Grid Computing (PDGC), Solan, India, 2018, pp. 215-220, doi: 10.1109/PDGC.2018.8745903.
Reya Sharma, Baij Nath Kaushik and Naveen Kumar Gondhi, 2018. Devanagari and Gurmukhi Script Recognition in the Context of Machine Learning Classifiers. Journal of Artificial Intelligence, 11: 65-70. DOI: 10.3923/jai.2018.65.70
D. Sudarsan, P. Vijayakumar, S. Biju, S. Sanu and S. K. Shivadas, "Digitalization of Malayalam Palmleaf Manuscripts Based on Contrast-Based Adaptive Binarization and Convolutional Neural Networks," 2018 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), Chennai, India, 2018, pp. 1-4, doi: 10.1109/WiSPNET.2018.8538588.
A. Shahkolaei, A. Beghdadi, S. Al-maadeed and M. Cheriet, "MHDID: A Multi-distortion Historical Document Image Database," 2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR), London, UK, 2018, pp. 156-160, doi: 10.1109/ASAR.2018.8480372.
S. Bhat and G. Seshikala, "Preprocessing and Binarization of Inscription Images using Phase Based Features," 2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC), Bangalore, India, 2018, pp. 1-6, doi: 10.1109/ICAECC.2018.8479434.
]H. T. Weldegebriel, H. Liu, A. U. Haq, E. Bugingo and D. Zhang, "A New Hybrid Convolutional Neural Network and eXtreme Gradient Boosting Classifier for Recognizing Handwritten Ethiopian Characters," in IEEE Access, vol. 8, pp. 17804-17818, 2020, doi: 10.1109/ACCESS.2019.2960161.
A. M. Menon, E. Eldho, G. M. Benny and D. Sudarsan, "A Novel Approach for Noise Removal from Hand Written Manuscript using Enhanced Gibbs Sampling Algorithm," 2019 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET), Chennai, India, 2019, pp. 497-500, doi: 10.1109/WiSPNET45539.2019.9032758.
An Insight of Script Text ExtractionPerformanceusing Machine LearningTechniques, November 2019, International Journal of Innovative Technology and Exploring Engineering Volume-9(issue-1):2581-2588, DOI:10.35940/ijitee.A5224.119119
Singh, A., & Kushwaha, A. (2019). Analysis of Segmentation Methods for Brahmi Script. DESIDOC Journal of Library & Information Technology, 39(2), 109-116. https://doi.org/10.14429/djlit.39.2.13615
Demilew, F.A., Sekeroglu, B. Ancient Geez script recognition using deep learning. SN Appl. Sci. 1, 1315 (2019). https://doi.org/10.1007/s42452-019-1340-4
N. Babu and S. A., "Character Recognition in Historical Handwritten Documents – A Survey," 2019 International Conference on Communication and Signal Processing (ICCSP), Chennai, India, 2019, pp. 0299-0304, doi: 10.1109/ICCSP.2019.8697988.
S. Wickramarathna and L. Ranathunga, "Data Driven Approach to Brahmi OCR Error Correction and Sinhala Meaning Generation from Brahmi Character Array," 2019 19th International Conference on Advances in ICT for Emerging Regions (ICTer), Colombo, Sri Lanka, 2019, pp. 1-6, doi: 10.1109/ICTer48817.2019.9023763.
George, Jossy P.. “Feature Extraction and Classification Techniques of MODI Script Character Recognition.” (2019), Corpus ID: 220050328
K. A. S. A. Nilupuli Wijerathna et al., "Recognition and translation of Ancient Brahmi Letters using deep learning and NLP," 2019 International Conference on Advancements in Computing (ICAC), Malabe, Sri Lanka, 2019, pp. 226-231, doi: 10.1109/ICAC49085.2019.9103340.
Yannis Assael, Thea Sommerschield, and Jonathan Prag. 2019. Restoring ancient text using deep learning: a case study on Greek epigraphy. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6368–6375, Hong Kong, China. Association for Computational Linguistics.
M. W. A. Kesiman, "Word Recognition for the Balinese Palm Leaf Manuscripts," 2019 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom), Banda Aceh, Indonesia, 2019, pp. 72-76, doi: 10.1109/CYBERNETICSCOM.2019.8875634.
[26]Chendage, Bapu & Mente, Rajivkumar & Magar, Vikas. (2020). A Survey on Ancient Marathi Script Recognition from Stone Inscriptions. Compliance Engineering. 11. 142.
S. Joseph and J. George, "Handwritten Character Recognition of MODI Script using Convolutional Neural Network Based Feature Extraction Method and Support Vector Machine Classifier," 2020 IEEE 5th International Conference on Signal and Image Processing (ICSIP), Nanjing, China, 2020, pp. 32-36, doi: 10.1109/ICSIP49896.2020.9339435.
Susan, S., & Malhotra, J. (2020). Recognising Devanagari Script by Deep Structure Learning of Image Quadrants. DESIDOC Journal of Library & Information Technology, 40(05), 268-271. https://doi.org/10.14429/djlit.40.05.16336
F. Damayanti, Y. K. Suprapto and E. M. Yuniarno, "Segmentation of Javanese Character in Ancient Manuscript using Connected Component Labeling," 2020 International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM), Surabaya, Indonesia, 2020, pp. 412-417, doi: 10.1109/CENIM51130.2020.9297954.
S. Samarajeewa and L. Ranathunga, "An Approach for Resolving Double Character Segmentation in Sinhala Social Media Text Images," 2020 From Innovation to Impact (FITI), Colombo, Sri Lanka, 2020, pp. 1-6, doi: 10.1109/FITI52050.2020.9424892.
N. Saxena and S. Chauhan, "Transformation of handwritten Devnagari script into word editable form using CNN," 2020 2nd International Conference on Advances in Computing, Communication Control and Networking (ICACCCN), Greater Noida, India, 2020, pp. 734-738, doi: 10.1109/ICACCCN51052.2020.9362824.
Gautam, Neha & Chai, Soo See & Jose, Jais. (2020). Recognition of Brahmi Words by Using Deep Convolutional Neural Network. 10.20944/preprints202005.0455.v1.
Mahajan Kirti, Tajne Niket, An Ancient Indian Handwritten Script Character Recognition by Using Deep Learning Algorithm, 2021/10/06.
N. Jayanthi, T. Sharma, V. Sharma, S. Tyagi and S. Indu, "Classification of ancient inscription images on the basis of material of the inscriptions," 2021 3rd International Conference on Signal Processing and Communication (ICPSC), Coimbatore, India, 2021, pp. 422-427, doi: 10.1109/ICSPC51351.2021.9451641.
P.Premi a ,R.Madhumithab, N.R.Raajan, "CNN based Digital alphanumeric archaeolinguistics apprehension for ancient script detection", Turkish Journal of Computer and Mathematics Education, Vol.12 No.6(2021), 5320-5326
[36]S. Ezhilarasi and P. U. Maheswari, "Depicting a Neural Model for Lemmatization and POS Tagging of Words from Palaeographic Stone Inscriptions," 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, 2021, pp. 1879-1884, doi: 10.1109/ICICCS51141.2021.9432315.
M. S. Deshmukh and S. R. Kolhe, "Unsupervised Page Area Detection Approach for the Unconstrained Chronic Handwritten Modi Document Images," 2021 International Conference on Emerging Smart Computing and Informatics (ESCI), Pune, India, 2021, pp. 130-135, doi: 10.1109/ESCI50559.2021.9396968.
P. D. Devi and V. Sathiyapriya, "Brahmi Script Recognition System using Deep Learning Techniques," 2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India, 2021, pp. 1346-1349, doi: 10.1109/ICIRCA51532.2021.9544978.
Mukerem Ali Nur, Mesfin Abebe, Rajesh Sharma Rajendran, "Handwritten Geez Digit Recognition Using Deep Learning", Applied Computational Intelligence and Soft Computing, vol. 2022, Article ID 8515810, 12 pages, 2022. https://doi.org/10.1155/2022/8515810
Raghunath Dey, Rakesh Chandra Balabantaray, and Sanghamitra Mohanty. 2022. Offline Odia handwritten character recognition with a focus on compound characters. Multimedia Tools Appl. 81, 8 (Mar 2022), 10469–10495. https://doi.org/10.1007/s11042-022-12148-z
Premanand Ghadekar; Khushi Jhanwar; Akash Sivanandan; Tanishka Shetty; Ameya Karpe; Prannay Khushalani, “ASR for Indian regional language using Nvidia’s NeMo toolkit,” AIP Conf. Proc. 2851, 020004 (2023), Vol 2851, issue 1, pp-1-14, 17th Nov 2023. DOI- https://doi.org/10.1063/5.0178629 Location NSHM, Durgapur, India.
P. Ghadekar, N. Malwatkar, N. Sontakke and N. Soni, "Comparative Analysis of LSTM, GRU and Transformer Models for German to English Language Translation," 2023 3rd Asian Conference on Innovation in Technology (ASIANCON), Ravet IN, India, 2023, pp. 1-7. INSPEC Accession Number: 23864094, Published on-10th Oct 2023. DOI - https://doi.org/10.1109/ASIANCON58793.2023.10270018
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
