AI-Driven Model for Converting Modi Lipi Documents into the English Language

Modi Lipi is an old, cursive script used for centuries to write records in the Maratha Empire and neighbouring regions from approximately the 13th to the early 20th century. Today, hundreds of thousands of these documents are stuck in archives because very few people can still read them. To fix this, through this paper researcher created ModiAnuwad, an AI system model that automatically reads these handwritten scripts and translates them into English. The process works in five steps: it cleans up the document images, breaks them into individual characters, identifies them using a powerful neural network, translates the text using a "Transformer" model (similar to the tech behind ChatGPT), and then fixes any grammar mistakes.

Modi Lipi; Historical document recognition; OCR, ANN

1. Patel, C.I., & Shah, D.B. (2015). Automatic recognition of Modi script using template matching and chain code features. International Journal of Computer Applications, 120(9), 1–8. Gyan Ganga Institute of Technology, Jabalpur, India. [Google Scholar] [Crossref]

2. Pal, U., & Chaudhuri, B.B. (2004). Indian script character recognition: A survey. Pattern Recognition, 37(9), 1887–1899. Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India. [Google Scholar] [Crossref]

3. Barve, A.B., Patil, S.S., & Kulkarni, A.V. (2017). Handwritten Modi script character recognition using HOG features and SVM classifier. In Proceedings of the International Conference on Information, Communication, Engineering and Technology (ICICET), Pune, India, pp. 1–5. Savitribai Phule Pune University, Pune, India. [Google Scholar] [Crossref]

4. Chaudhuri, B.B., & Pal, U. (1998). A complete printed Bangla OCR system. Pattern Recognition, 31(5), 531–549. Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India. [Google Scholar] [Crossref]

5. Kulkarni, V.B., Jadhav, M.S., & Kolhe, S.L. (2020). Modi character recognition using deep convolutional neural network. International Journal of Advanced Computer Science and Applications, 11(4), 229–236. North Maharashtra University, Jalgaon, India. [Google Scholar] [Crossref]

6. Deshmukh, R., & Bhirud, S.G. (2019). Word sense disambiguation for Marathi language using graph-based approach. International Journal of Intelligent Systems and Applications, 11(3), 40–49. Veermata Jijabai Technological Institute, Mumbai, India. [Google Scholar] [Crossref]

7. Kunchukuttan, A., Mehta, P., & Bhattacharyya, P. (2018). The IIT Bombay English-Hindi parallel corpus. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC), Miyazaki, Japan, pp. 3965–3970. Indian Institute of Technology Bombay, Mumbai, India. [Google Scholar] [Crossref]

8. Deshpande, P.S., Malik, L., & Arora, S. (2008). Fine-classification and recognition of hand-written Devnagari characters with regular expressions and minimum edit distance method. Journal of Computers, 3(5), 11–17. Indian Institute of Information Technology, Allahabad, India. [Google Scholar] [Crossref]

9. Patil, H., & Bhirud, S. (2018). Marathi language processing: Review of morphological analysis tools. International Journal of Applied Engineering Research, 13(6), 3638–3644. Veermata Jijabai Technological Institute, Mumbai, India. [Google Scholar] [Crossref]

10. Sharma, N., Pal, U., Kimura, F., & Pal, S. (2006). Recognition of off-line handwritten Devnagari characters using quadratic classifier. In Proceedings of the Indian Conference on Computer Vision, Graphics & Image Processing, Madurai, India, pp. 805–816. Indian Statistical Institute, Kolkata, India. [Google Scholar] [Crossref]

11. Jayadevan, R., Kolhe, S.R., Patil, P.M., & Pal, U. (2011). Offline recognition of Devanagari script: A survey. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 41(6), 782–796. Shivaji University, Kolhapur, Maharashtra, India. [Google Scholar] [Crossref]

• Evaluating the Impacts of Mind Mapping Strategy on Developing EFL Students’ Critical Reading Skills
• Significance of Reading Instructions for Language Improvement in Children with Down Syndrome
• Prenasalised Consonants in Liangmai
• Metadiscourse Matters: Definitions, Models, and Advantages for ESL/ EFL Writing
• Blank Minds and Stuck Voices: Understanding and Addressing Cognitive Anxiety in High-Stakes ESL Speaking Tests