OCR in Indian Languages

Conference: International Conference on Soft Computing Applications in Wireless Communication
Author(s): Abhishek Verma, Suket Arora, Preeti Verma Year: 2017
Grenze ID: 02.SCAWC.2017.1.507 Page: 192-202


Optical Character Recognition or OCR is the electronic translation of handwritten, typewritten or printed text into\nmachine translated images. Optical Character Recognition (OCR) is a very important task in Pattern Recognition. Foreign\nlanguages, especially English character recognition has been extensively studied by many researches but due to complication\nof Indian Languages like Hindi ,Punjabi ,teulgu ,malyalam etc. the research work is very limited and constrained. This paper\npresents the research work related to all Indian languages, various approaches to character recognition along with some\napplications of character recognition is also discussed in this paper. The aim of this paper is to provide an overview of the\nresearch going on in Indian script OCR systems. This survey paper has been felt necessary when the research on OCRs for\nIndian scripts is still a challenging task. Hence, a brief introduction to the general OCR and typical steps in the development\nof an OCR are given in this paper, along with a brief description of the different techniques used in them. This paper is\nprepared to be as self sufficient, and complete as possible, so that it provides a starting point for the researchers entering into\nthis area.


SCAWC - 2017