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

• Published in: Proceedings - International Conference on Image Processing pp. 3963 - 3967
• Main Authors: Chandra Prakash, Konkimalla, Srikar, Y. M., Trishal, Gayam, Mandal, Souraj, Channappayya, Sumohana S.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2018
• Subjects: Character recognition; Convolutional neural network; Deep learning; Document Recognition; Image segmentation; Machine learning; Neural networks; OCR; Optical character recognition software; Optical imaging; Telugu; Training
• ISSN: 2381-8549
• DOI: 10.1109/ICIP.2018.8451438

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, our code has been made freely available at this link.