Skip to main content

Stamp processing package

Project description

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 for the stamp detection model and fastai Unet for stamp removal model

Install

Due to the requirements of the used libraries, stamp-processing requires Python 3.8 or higher.

stamp-processing is published on Pypi. To install the package, use pip:

pip install stamp_processing

Note: This package uses PyTorch. If you need GPU support, you may want to install PyTorch with CUDA support first:

pip install torch torchvision --index-url https://download.pytorch.org/whl/cu118
pip install stamp_processing

How to use

Check out example for basic usage or run getting_started.ipynb in the example folder for example usage.

Documentation

Documentation will be available soon.

Changelog

See CHANGELOG.md for version history and breaking changes.

Contact

Create an issue if you run into any bug or want to suggest a feature on Github

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

better_stamp_processing-0.1.dev46.tar.gz (7.7 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

better_stamp_processing-0.1.dev46-py3-none-any.whl (35.1 kB view details)

Uploaded Python 3

File details

Details for the file better_stamp_processing-0.1.dev46.tar.gz.

File metadata

File hashes

Hashes for better_stamp_processing-0.1.dev46.tar.gz
Algorithm Hash digest
SHA256 3bb840e554106d9d5f23bc2a847831cf85e524fcaa7ff7526138a7dd02ab291c
MD5 8b54ac97404315bd0c59fe55e43492cd
BLAKE2b-256 656b2b3f66afd36a6b8cac37940043bfd22bfbafb0af20ad57e418731dbef952

See more details on using hashes here.

File details

Details for the file better_stamp_processing-0.1.dev46-py3-none-any.whl.

File metadata

File hashes

Hashes for better_stamp_processing-0.1.dev46-py3-none-any.whl
Algorithm Hash digest
SHA256 6b05c90274c63f013994313991a3e09117d4b21a7332b814d724f5d7623f0e94
MD5 1bf364bb07c865391d7fb5d87fa31ec2
BLAKE2b-256 02f030217885f924389f9dde309b70f50e68b968e46bc8c4f7cf77b1ad59cdf7

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page