Add model, configuration files and description (#1)

- Add model, configuration files and description (46954747b3693a724ca4054210de985f013b1a5d)


Co-authored-by: Mélodie Boillet <[email protected]>

README.md

@@ -1,3 +1,78 @@
 ---
+library_name: Doc-UFCN
 license: mit
+tags:
+- Doc-UFCN
+- PyTorch
+- Object detection
+metrics:
+- IoU
+- F1
+- [email protected]
+- [email protected]
+- AP@[.5,.95]
 ---
+
+
+# Generic historical line detection
+
+The generic historical line detection model predicts text lines from document images.
+
+## Model description
+
+The model has been trained using the Doc-UFCN library on 10 historical document datasets including these public datasets:
+  * [Bozen](https://zenodo.org/record/218236)
+  * [cBAD2017 (READ)](https://zenodo.org/record/1491441)
+  * [cBAD2019](https://zenodo.org/record/2567398)
+  * [DIVA-HisDB](https://diuf.unifr.ch/main/hisdoc/diva-hisdb.html)
+  * [Horae](https://github.com/oriflamms/HORAE/)
+  * [ScribbleLens](https://www.openslr.org/84/)
+
+It has been trained on images with their largest dimension equal to 768 pixels, keeping the original aspect ratio.
+
+## Evaluation results
+
+The model achieves the following results on the test sets:
+
+|                         | IoU   | F1    | AP@[.5] | AP@[.75] | AP@[.5,.95] |
+| ----------------------- | ----- | ----- | ------- | -------- | ----------- |
+| Bozen                   | 60.15 | 75.10 | 97.14   | 3.79     | 27.50       |
+| cBAD2017 (READ) Complex | 46.79 | 60.35 | 56.01   | 3.40     | 16.26       |
+| cBAD2017 (READ) Simple  | 53.97 | 68.43 | 57.26   | 8.45     | 19.39       |
+| cBAD2019                | 50.77 | 64.52 | 35.46   | 2.88     | 11.51       |
+| DIVA-HisDB              | 41.54 | 57.88 | 63.15   | 0.00     | 11.69       |
+| Horae                   | 48.93 | 63.95 | 57.45   | 5.20     | 15.55       |
+| ScribbleLens            | 76.61 | 86.72 | 98.02   | 71.87    | 58.32       |
+
+The model has been trained to reduce mergers in predictions (see the [paper](https://link.springer.com/article/10.1007/s10032-022-00395-7) for more details on training). Therefore, despite slightly low evaluation values, the model correctly detects lines on a wide variety of historical and modern manuscript documents.
+
+## How to use
+
+Please refer to the Doc-UFCN library page (https://pypi.org/project/doc-ufcn/) to use this model.
+
+# Cite us!
+
+```bibtex
+@inproceedings{boillet2022,
+    author = {Boillet, Mélodie and Kermorvant, Christopher and Paquet, Thierry},
+    title = {{Robust Text Line Detection in Historical Documents: Learning and Evaluation Methods}},
+    booktitle = {{International Journal on Document Analysis and Recognition (IJDAR)}},
+    year = {2022},
+    month = Mar,
+    pages = {1433-2825},
+    doi = {10.1007/s10032-022-00395-7}
+}
+```
+
+```bibtex
+@inproceedings{boillet2020,
+    author = {Boillet, Mélodie and Kermorvant, Christopher and Paquet, Thierry},
+    title = {{Multiple Document Datasets Pre-training Improves Text Line Detection With
+              Deep Neural Networks}},
+    booktitle = {2020 25th International Conference on Pattern Recognition (ICPR)},
+    year = {2021},
+    month = Jan,
+    pages = {2134-2141},
+    doi = {10.1109/ICPR48806.2021.9412447}
+}
+```

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d0659a29638446f573bec8928f3380f8643f4bee5c9ea7b8e64ae813dcc6f5
+size 49198561

parameters.yml

@@ -0,0 +1,11 @@
+---
+version: 0.0.1
+parameters:
+  mean: [194, 185, 160]
+  std: [49, 49, 47]
+  min_cc: 50
+  classes:
+    - background
+    - text_line
+  input_size: 768
+