sbb_binarization/README.md

37 lines
1.1 KiB
Markdown
Raw Normal View History

2020-01-15 19:49:18 +01:00
# Binarization
2020-01-15 19:49:18 +01:00
> Binarization for document images
2019-12-10 13:00:05 +01:00
# Examples
2020-10-29 00:47:23 +01:00
<img src="https://user-images.githubusercontent.com/952378/63592437-e433e400-c5b1-11e9-9c2d-889c6e93d748.jpg" width="190"><img src="https://user-images.githubusercontent.com/952378/63592435-e433e400-c5b1-11e9-88e4-3e441b61fa67.jpg" width="190"><img src="https://user-images.githubusercontent.com/952378/63592440-e4cc7a80-c5b1-11e9-8964-2cd1b22c87be.jpg" width="230"><img src="https://user-images.githubusercontent.com/952378/63592438-e4cc7a80-c5b1-11e9-86dc-a9e9f8555422.jpg" width="230">
2020-01-15 19:49:18 +01:00
## Introduction
This tool performs document image binarization (i.e. transform colour/grayscale
to black-and-white pixels) for OCR using multiple trained models.
2019-12-10 13:00:05 +01:00
2020-01-15 19:49:18 +01:00
## Installation
Clone the repository, enter it and run
`pip install .`
2020-01-15 19:49:18 +01:00
2020-01-16 15:56:32 +01:00
### Models
2020-09-16 22:10:47 +02:00
Pre-trained models can be downloaded from here:
2020-01-16 15:47:52 +01:00
https://qurator-data.de/sbb_binarization/
2020-01-15 19:49:18 +01:00
## Usage
```sh
sbb_binarize \
--patches \
-m <directory with models> \
<input image> \
<output image>
```
**Note** In virtually all cases, the `--patches` flag will improve results.