Previous research in Document Analysis and OCR has focused on English text, and Indian languages have mainly been ignored. Our purpose is to create end-to-end document analysis tools for Indic language documents, called Indic Document Analysis, which can enable effective and accurate OCR and digitization.

A key objective of the project is to develop a user-friendly interface through which the user will be able to convert scanned images and pdf files into machine-coded text, which can be further refined to recognize more complex characters and better detect languages. Additionally, this tool can be used to post-edit documents and make them more effective and engaging.

Named Entity Recognition (NER) is a method of information extraction that is used to acquire important information from unstructured text documents. In this project, our aim is to develop a NER extractor for scanned medical documents using NLP techniques.