A naive ocr that uses Artificial Neural Network built from scratch.
python3
and virtualenv
for python3 are used
virtualenv ocr
cd
into the new directory ocr
source bin/activate
You should be able to see the name of the environment after the activation
pip install -r requirements.txt
- Download the data from https://drive.google.com/open?id=1MExqrcMutclcYtPZV3vc1n1RFHxqnouT
- Put the data as data/
Run ocr.py
as:
python ocr.py
To test the ocr, you have to put a .jpg image inside data/ as test.jpg.
The script tries to test the image from the path data/test.jpg accordingly.