14-10-2014, 01:42 PM
Abstracts: Optical Character Recognition (OCR) is a technology that enables to convert different types of documents, such as scanned paper documents, PDF ?les or images captured by a digital camera into editable and searchable data. In recent years, OCR technology has been applied to the wide spectrum of industries, revolutionizing the document management process. OCR has facilitated scanned documents to become more than just image ?les, turning into fully searchable documents with text content which can be recognized by computers. The tedious work of manually retyping of any document can be avoided by the use of OCR as OCR extracts the details and prepares electronic database. The output is accurate, ef?cient, reliable and time saving.This research work based on MATLAB platform is intended to develop an OCR system recognizing Indian Languages. As Indian people and Indian languages are making their mark in the global arena, this work will prove to be major breakthrough in the ?eld of OCR.