Update README.md

README.md

@@ -1,6 +1,6 @@
-# Binarization
+# sbb_binarization
 
-> Binarization for document images
+> Document Image Binarization using pre-trained models
 
 [![pip release](https://img.shields.io/pypi/v/sbb-binarization.svg)](https://pypi.org/project/sbb-binarization/)
 [![CircleCI test](https://circleci.com/gh/qurator-spk/sbb_binarization.svg?style=shield)](https://circleci.com/gh/qurator-spk/sbb_binarization)
@@ -10,28 +10,35 @@
 
 <img src="https://user-images.githubusercontent.com/952378/63592437-e433e400-c5b1-11e9-9c2d-889c6e93d748.jpg" width="180"><img src="https://user-images.githubusercontent.com/952378/63592435-e433e400-c5b1-11e9-88e4-3e441b61fa67.jpg" width="180"><img src="https://user-images.githubusercontent.com/952378/63592440-e4cc7a80-c5b1-11e9-8964-2cd1b22c87be.jpg" width="220"><img src="https://user-images.githubusercontent.com/952378/63592438-e4cc7a80-c5b1-11e9-86dc-a9e9f8555422.jpg" width="220">
 
-## Introduction
-
-This tool performs document image binarization using a trained ResNet50-UNet model. 
-
 ## Installation
 
-Clone the repository, enter it and run
+Python versions `3.7-3.10` are currently supported.
 
-`pip install .`
+You can either install via 
 
-### Models
+```
+pip install sbb-binarization
+```
 
-Pre-trained models in HDF5 format can be downloaded from here:
+or clone the repository, enter it and install (editable) with
 
-https://qurator-data.de/sbb_binarization/
+```
+git clone git@github.com:qurator-spk/sbb_binarization.git
+cd sbb_binarization; pip install -e .
+```
 
-We also provide models in Tensorflow SavedModel format via Huggingface and Github release assets:
+### Models
 
-https://huggingface.co/SBB/sbb_binarization
+Pre-trained models can be downloaded from the locations below. We also provide the models and [model card](https://huggingface.co/SBB/sbb_binarization) on 🤗 
-https://github.com/qurator-spk/sbb_binarization/releases
 
-With [OCR-D](https://ocr-d.de/), you can use the [Resource Manager](Tensorflow SavedModel) to deploy models, e.g.
+| Version   |      Format      |  Download |
+|----------|:-------------:|-------|
+| 2021-03-09 |  `SavedModel` | https://github.com/qurator-spk/sbb_binarization/releases/download/v0.0.11/saved_model_2021_03_09.zip |
+| 2021-03-09 |  `HDF5` | https://qurator-data.de/sbb_binarization/2021-03-09/models.tar.gz |
+| 2020-01-16 | `SavedModel` | https://github.com/qurator-spk/sbb_binarization/releases/download/v0.0.11/saved_model_2020_01_16.zip |
+| 2020-01-16 |  `HDF5` | https://qurator-data.de/sbb_binarization/2020-01-16/models.tar.gz |
+
+With [OCR-D](https://ocr-d.de/), you can use the [Resource Manager](https://ocr-d.de/en/models) to deploy models, e.g.
 
     ocrd resmgr download ocrd-sbb-binarize "*"
 
@@ -40,11 +47,13 @@ With [OCR-D](https://ocr-d.de/), you can use the [Resource Manager](Tensorflow S
 
 ```sh
 sbb_binarize \
-  -m <path to directory containing model files \
+  -m <path to directory containing model files> \
   <input image> \
   <output image>
 ```
 
+**Note:** the output image MUST use either `.tif` or `.png` as file extension to produce a binary image. Input images can also be JPEG.
+
 Images containing a lot of border noise (black pixels) should be cropped beforehand to improve the quality of results.
 
 ### Example
@@ -65,6 +74,6 @@ For simple smoke tests, the following will
 - download test data
 - run the OCR-D wrapper (on page and region level):
     
-        make model
+        make models
         make test