A comparison study on optical character recognition models in mathematical equations and in any language

Abstract

Optical Character Recognition[OCR] is a technology that makes use of artificial intelligence and machine learning to extract readable text from documents, images, tags or any other type of sources. It allows one to convert characters and text objects into digital data that can be easily processed, analyzed, and modified. OCR can be applied to various types of languages in both written and spoken format. It can process everything from hand-written documents to typed-out text, making it a highly versatile technology. OCR makes use of a variety of algorithms and methods to process images, and then produces readable output, whatever language it is used for. This technology has the potential to be used for industries, banking, the medical field, security, and document storage among others. OCR faces significant challenges in accurately predicting language and mathematical expressions due to variations in handwriting styles, complex layouts, and the ambiguity of symbols. In this research, we propose assessing the results of different models that have been trained to identify an improved OCR system. The best OCR model is With the help of a decision tree model chosen.