Recognition of Ancient Tamil Characters from Epigraphical inscriptions using Raspberry Pi based Tesseract OCR

Authors

  • M. Merline Magrina  Assistant Professor, Department of ECE, Er. Perumal Manimekalai College of Engineering, Hosur, TamilNadu, , India

DOI:

https://doi.org/10.32628/CSEIT217230

Keywords:

ANN, Character Segmentation, Character Recognition, Open CV- python, Raspberry Pi, Tesseract OCR, Unicode values.

Abstract

Optical Character Recognition (OCR) is the process of identification of the printed text using photoelectric devices and computer software. It converts the inscribed text on the stones into machine encoded format. OCR is widely used in machine learning process like cognitive computing, machine translation, text to speech conversion and text mining.OCR is mainly used in the research fields like Character Recognition, Artificial Intelligence and Computer Vision. In this research, the recognition process is done using OCR, the inscribed character is processed using Raspberry Pi device on which it recognizes characters using Artificial Neural Network. This work mainly focuses on the recognition of ancient Tamil characters inscribed on stones to modern Tamil characters belong to 9th and 12th century characters. The input image is subjected to gray scale conversion process and enhanced using adaptive thresholding process. The output image is subjected to thinning process to reduce the pixel size of the image. Then the characters are classified using Artificial Neural Network Architecture and the classified characters are mapped to modern Tamil character using Unicode. The Artificial Neural Network has input layer, hidden layer of 15 neurons and output layer of 1 neuron to classify the characters. The accuracy of the constructed system for the recognition of epigraphical inscriptions is calculated. The above process is carried out in raspbian environment using python process.

References

  1. Anush Goel, Akash Sehrawat, Ankush Patil, Prashant Chougule and Supriya Khatavkar (2018), “Raspberry Pi based reader for blind people”, International Research Journal of Engineering and Technology (IRJET 2018), vol: 5, issue: 6, pp: 1639- 1642. 
  2. Elumalai .G, J. Sundar Rajan, P. Surya Prakash, V.L. Susruth and P.K. Sudharsanan (2018), “Design and Development of Tessaract– OCR based assistive system to convert captured text into voice output”, International Research Journal of Engineering and Technology (IRJET 2018), vol: 5, issue: 4, pp: 509 – 513.
  3. Thiyagarajan, Saravanan Kumar, Praveen Kumar and Sakana (2018), “Implementation of Optical Character Recognition using Raspberry Pi for visually Challenged People”, International Journal of Engineering & Technology (IJET 2018), vol: 7, issue: 3, pp: 65 – 67.
  4. Vishwanath Bharadwaja, Ananmy, Sarraf Nikhil, Vineetha (2018), “Implementation of Artificial Neural Network on Raspberry Pi for signal processing applications”, International Conference on Advances in Computing, Communications & Informatics (ICACCI 2018), pp: 1488 – 1491.
  5. Beihai Tan, Chao Hu and Zepei Zhang (2017), “Character Recognition based on Corner Detection”, IEEE International Conference on Natural computation, Fuzzy System and Knowledge Discovery (ICNC-FSKD), pg: 503-507.
  6. Bhavani. B (2017), “Tamilnadu Historical Documents (Epigraphical Inscriptions)”.
  7. Das T.K., Asis Kumar Tripathy and Alekha Kumar Mishra (2017), “Optical Character Recognition using Artificial Neural Network”, International Conference on Computer Communication & Informatics (ICCCI 2017), pp: 1-4.
  8. DurgaDevi. K and Uma Maheswari (2017), “Insight on Character Recognition for calligraphy digitization”, IEEE International Innovations in ICT for Agriculture and Rural Development (TIAR), pp: 78-89.
  9. Mallapa D.Gurav, Shruthi S.Salimath, Shruthi B.Hatti and Vijayalakshmi I.Byakod (2017), “ B-Light A Reading aid for the Blind people using OCR & OpenCV”, International Journal of Scientific Research Engineering & Technology (IJSRET 2017), vol: 6, issue: 5, pp: 546 – 548.
  10. Praveen Kumar, Padmaja, Nagadeepa and Sagar Reddy (2017), “Online English Character Recognition using Raspberry Pi”, International Journal of Scientific Engineering & Technology Research (IJSETR 2017), vol: 6, issue: 20, pp: 3978-3981.
  11. Rajasekar. M, Celine Kavitha and Anto Bennet.M (2016), “Performance and analysis of Handwritten Tamil Character Recognition using Artificial Neural Network”, International Journal of Recent Scientific Research (IJRST), vol: 7, pp: 8611-8615.
  12. Sushama Shelke, Shaila Apte (2016), “ Real time character reading system for Marathi script using Raspberry Pi”, 3rd International Conference on Electrical, Electronics, Engineering, Trends, Communication, Optimization & Sciences (EEECOS 2016), pp: 1 – 5.
  13. Balasubramanie.P and Vellingiriraj. E.K (2015), “Recognition of ancient Tamil Historical documents by Boolean Matrix & BFS graph”, International Journal of Computer Science & Technology, vol: 5, pp:65-68.
  14. Preethi. N and Gunasekaran. T (2015), “Language Specific Offline character recognition using Neural Network Classifier”, International Journal of Advanced Research in Electronics & Communication Engineering (IJARECE), vol: 4, pp: 218-221.
  15. Ajantha Devi and Santhosh Baboo (2014), “Embedded Optical Character Recognition on Tamil Text Image using Raspberry Pi”, International Journal of Computer Science Trends & Technology (IJCST 2014), vol: 2, issue: 4, pp: 127 – 131.
  16. Pranjali Pohankar, Namrata Taralkar, Snehalata Karmare and Smita Kulkarni (2014), “Character Recognition using Artificial Neural Network”, International Journal of Electronics Engineering & Computer Engineering (IJECCE 2014), vol: 5, issue: 4, pp: 245 – 248.
  17. Ankit Sharma, Dipti. R. Chaudhary (2013), “Character Recognition using Neural Network”, International Journal of Engineering Trends & Technology (IJETT 2013), vol: 4, issue: 4, pp: 662 – 667.
  18. https://www.pyimagesearch.com/2018/09/17/opencv-ocr-and-text-recognition-with-tesseract/
  19. https://www.geeksforgeeks.org/implementing-ann-training-process-in-python/
  20. https://towardsdatascience.com/how-to-build-your-own-neural-network-from-scratch-in-python-68998a08e4f6
  21. https://www.python-course.eu/neural_networks_with_python_numpy.php
  22. https://www.geeksforgeeks.org/neural-networks-a-beginners-guide/

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2021-04-30

Issue

Volume 7, Issue 2, March-April-2021

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
M. Merline Magrina, " Recognition of Ancient Tamil Characters from Epigraphical inscriptions using Raspberry Pi based Tesseract OCR" International Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 7, Issue 2, pp.118-127, March-April-2021. Available at doi : https://doi.org/10.32628/CSEIT217230