Pixelwise binarization with selectional auto-encoders in Keras

Project description

Binarization

Binarization for document images

Examples

Introduction

This tool performs document image binarization (i.e. transform colour/grayscale to black-and-white pixels) for OCR using multiple trained models.

The method used is based on Calvo-Zaragoza/Gallego, 2018. A selectional auto-encoder approach for document image binarization.

Installation

Clone the repository, enter it and run

pip install .

Models

Pre-trained models can be downloaded from here:

https://qurator-data.de/sbb_binarization/

Usage

sbb_binarize \
  --patches \
  -m <directory with models> \
  <input image> \
  <output image>

Note In virtually all cases, the --patches flag will improve results.

Project details

Release history Release notifications | RSS feed

0.1.0

Apr 14, 2023

0.0.11

Oct 24, 2022

0.0.10

Jul 21, 2022

0.0.9

Apr 26, 2022

0.0.8

May 7, 2021

0.0.7

May 7, 2021

0.0.6

Nov 23, 2020

This version

0.0.5

Nov 2, 2020

0.0.4

Oct 27, 2020

0.0.3

Oct 23, 2020

0.0.2

Oct 23, 2020

0.0.1

Oct 22, 2020

Download files

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

Source Distribution

sbb_binarization-0.0.5.tar.gz (5.8 kB view details)

Uploaded Nov 2, 2020 Source

Built Distribution

sbb_binarization-0.0.5-py3-none-any.whl (11.7 kB view details)

Uploaded Nov 2, 2020 Python 3

File details

Details for the file sbb_binarization-0.0.5.tar.gz.

File metadata

Download URL: sbb_binarization-0.0.5.tar.gz
Upload date: Nov 2, 2020
Size: 5.8 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/50.3.0 requests-toolbelt/0.9.1 tqdm/4.48.2 CPython/3.6.9

File hashes

Hashes for sbb_binarization-0.0.5.tar.gz
Algorithm	Hash digest
SHA256	`3d52934c45abfa8b4ac3b399c47fa23f6a2b42a141a0cf7cf541be77fbc5dd6d`
MD5	`7786ac743fbc24ab955b70dc0f5659bb`
BLAKE2b-256	`f73a3e5727865e1a24d09330c1f222667dd3f507f2a9fcc55ccecbf1fe0430b6`

See more details on using hashes here.

File details

Details for the file sbb_binarization-0.0.5-py3-none-any.whl.

File metadata

Download URL: sbb_binarization-0.0.5-py3-none-any.whl
Upload date: Nov 2, 2020
Size: 11.7 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/50.3.0 requests-toolbelt/0.9.1 tqdm/4.48.2 CPython/3.6.9

File hashes

Hashes for sbb_binarization-0.0.5-py3-none-any.whl
Algorithm	Hash digest
SHA256	`71c4d6fb17a120345833172fffcf7874809547760878b2e96d6dfb667b500479`
MD5	`cc590b73ab41f4f752946bcce69080e7`
BLAKE2b-256	`defcf95b18737adb313e3a5c677785d8279811c86c76862662914f86bfa3f0bc`