Optical Character Recognition (OCR) for Telugu: Database, Algorithm and Application

TL;DR

This paper introduces a new Telugu character database, a deep learning OCR algorithm tailored for Telugu script, and a client-server deployment solution, addressing the unique challenges posed by Telugu's complex script for improved recognition accuracy.

Contribution

The work provides the first comprehensive Telugu OCR system including a dedicated database, a specialized deep learning algorithm, and an online deployment framework.

Findings

Created a Telugu character database

Developed a deep learning-based OCR algorithm for Telugu

Deployed a client-server OCR solution for online use

Abstract

Telugu is a Dravidian language spoken by more than 80 million people worldwide. The optical character recognition (OCR) of the Telugu script has wide ranging applications including education, health-care, administration etc. The beautiful Telugu script however is very different from Germanic scripts like English and German. This makes the use of transfer learning of Germanic OCR solutions to Telugu a non-trivial task. To address the challenge of OCR for Telugu, we make three contributions in this work: (i) a database of Telugu characters, (ii) a deep learning based OCR algorithm, and (iii) a client server solution for the online deployment of the algorithm. For the benefit of the Telugu people and the research community, we will make our code freely available at https://gayamtrishal.github.io/OCR_Telugu.github.io/