Metadata-Version: 2.1
Name: stamp-processing
Version: 0.0.3
Summary: Stamp processing package
Home-page: https://github.com/sun-asterisk-research/stamp_processing/
Author: Sun* AI Research Team
Author-email: sun.converter.team@gmail.com
License: UNKNOWN
Project-URL: Bug Tracker, https://github.com/sun-asterisk-research/stamp_processing/issues
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Requires-Dist: gdown
Requires-Dist: Pillow (<=8.2.0opencv-python>=4.1.2.30)
Requires-Dist: torch (==1.8.1)
Requires-Dist: torchvision (==0.9.1)
Requires-Dist: fastai (==2.3.1)
Requires-Dist: numpy (>=1.20)
Requires-Dist: PyYAML (==5.4.1)

# Stamp Processing
> A package develop by Sun* AI Research Team as part of the PDF Converter project. 

This is a Deep Learning based package for detecting and removing stamp from document images.
This package uses  [Yolov5](https://github.com/ultralytics/yolov5) for the stamp detection model and [fastai](https://github.com/fastai/fastai) Unet for stamp removal model

## Install
Due to the requirements of the used libraries, stamp-processing requires version 3.7 or higher.

`stamp-processing` is published on [Pypi](https://pypi.org/project/stamp-processing/). To install the package, use `pip`:

`pip install stamp_processing`

## How to use
Check out [example](https://github.com/sun-asterisk-research/stamp_processing/blob/master/example/example.md) for basic usage or run  `getting_started.ipynb` in the `example` folder for example usage.

## Documentation
Documentation will be available soon.



## Contact 
Create an issue if you run into any bug or want to suggest a feature on [Github](https://github.com/sun-asterisk-research/stamp_processing)


