Tamil Character Recognition, Translation and Transliteration System 
M. Prakash1, Apoorva Ojha2, Priyanshu Raman3
1Priyanshu Raman*, Department of Computer Science and Engineering, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India.
2Apoorva Ojha, Department of Computer Science and Engineering, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India.
3Dr. M. Prakash, Associate Professor, Department of Computer Science and Engineering, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India.
Manuscript received on March 28, 2020. | Revised Manuscript received on April 25, 2020. | Manuscript published on April 30, 2020. | PP: 1762-1767 | Volume-9 Issue-4, April 2020. | Retrieval Number: D7633049420/2020©BEIESP | DOI: 10.35940/ijeat.D7633.049420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Optical Character Recognition (OCR) is the machine conversion of handwritten or typed data into machine encoded scripts. English, is the informal link to all the regional languages in India and is used to publish reports, papers, magazines and records. Monolingual systems are incapable of doing so, thus increasing the need of bilingual frameworks. We have created a character recognition system that converts the user’s input in the Tamil language to English. Additionally, we can also perform transliteration of Tamil to English and vice versa. The bilingual OCR system, “MOZHI VALLAAN,” which has an accuracy of 94%, will be used.
Keywords: Optical Character Recognition, Translation, Transliteration, Longest Common Subsequence, Inception V3.