Document OCR
By- Azfar Lari
Requirements
Python 3
Setup:
- Install the dependencies on linux
$ sudo apt install tesseract-ocr (Install Tesseract-OCR engine as given in the instructions: https://github.com/tesseract-ocr/tesseract)
- Install python dependencies:
pip3 install -r requirements.txt
Usage:
-
Use: python3 app.py to start the flask server
-
The file types are: "Aadhar Front", "Aadhar Back", "Cheque", "PAN"
-
It returns a JSON containing all the data
Note
Have provided Separate API for face matching.