Optical Character Recognition Technology using Machine Learning

Abstract

The creation of software that is capable of performing OCR in multiple languages is the goal of this project. The primary objective of optical character recognition (OCR) software is to convert pre-existing paper documents or picture files into digital versions that can be edited. Character and word detection are the two stages that are involved in the operation of multilingual OCR software. In the case of a method that is more complex, an OCR will additionally operate on the detection of sentences in order to maintain the structure of a document. Our project's goal was to better manage some of the more complicated recognition issues, such as distinct language alphabets, by better understanding, utilising, and improving the open source Optical Character Recognizer (OCR) software. This was our project's primary objective.