Medical Document Extracter

• It is Major project in the codebasics.io Python For Beginner course

Abstract

This project is aimed to extract the required data from the medical documents
using open-cv,OCR,pyTesseract,regex to extract text from documents.
FastApi(For Backend), AirTabel(For DataBase), Streamlit(For FrontEnd).

Algorithms

click here to get in-depth video

Installation

• you need to install the Tesseract-OCR and poppler

Tools

• open-cv used to extract text from shadow area

• numpy is used in cv2 adaptiveThreshold

• pyTesseract-ocr to extract text from img

• FastApi backend

• PDF2IMG converting pdf to img

• re for extract required text

Working on

• Streamlit used for frontend

• Airtable used for DataBase