Comprehensive study of deep learning based Telugu OCR: A survey

M. V. Vijaya Saradhi, K. Rakesh *, D. Ravi Prasanna, K. Swetha and B. Prawin

Department of Computer Science and Engineering, ACE Engineering College, Hyderabad, Telangana, India.
 
Research Article
International Journal of Science and Research Archive, 2023, 08(01), 353-356.
Article DOI: 10.30574/ijsra.2023.8.1.0050
Publication history: 
Received on 03 December 2022; revised on 14 January 2023; accepted on 17 January 2023
 
Abstract: 
There will be no computer-editable text in the image file. The method of optical character recognition (OCR), which can read handwritten or printed text in images, turns that text into a file that can be edited on a computer. English has a well-developed OCR system. OCR is currently required for Indian languages in order to process application forms, categorise books in libraries, and preserve historical records that are mostly written in Indian languages. The Telugu language presents challenges for OCR since each character is made up of a single consonant, a single vowel, or a compound of vowels and consonants.
 
Keywords: 
Text segmentation; Text Extraction; Image-based; Document processing; Convolution Neural Network; OCR
 
Full text article in PDF: 
 
Copyright information: 

Copyright © 2023 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0