Skip to content

kapitsa2811/pytorch-text-recognition

 
 

Repository files navigation

travis build

Text recognition tool

Text recognition with Pytorch Using CRNN and CRAFT pretrained models.

Main sources:

Install it, install requirements.txt by

python -m pip install requirements.txt

and check argparsers. at the moment it is only input image so

> source venv/Scripts/activate
> python app.py --input_file test_image.jpeg

Example results

image

return .json file with

{"0": "dollar", "1": "glen", "2": "and", "3": "campbeli", "4": "castle"}�0

Usage

You can clone this repository, set up your own virtual environment by


python -m venv venv

Activate it by

source venv/Scripts/activate

Install requirements using pip

python -m pip install -r requirements.txt

and run app.py


python app.py 

then go to

localhost:8000

and test it.

I decided to put it on simplest flask module only to show it's basic functionality.

To dos

add frontend and some fancy vis.

Releases

No releases published

Packages

No packages published

Languages

  • Python 98.6%
  • Other 1.4%