---
library_name: Doc-UFCN
license: mit
tags:
- Doc-UFCN
- PyTorch
- object-detection
- dla
- historical
- handwritten
metrics:
- IoU
- F1
- AP@.5
- AP@.75
- AP@[.5,.95]
pipeline_tag: image-segmentation
---

# Doc-UFCN - NorHand v1 - Line detection

The NorHand v1 line detection model predicts text lines from NorHand document images. This model was developed during the [HUGIN-MUNIN project](https://hugin-munin-project.github.io/).

## Model description

The model has been trained using the Doc-UFCN library on NorHand document images.
It has been trained on images with their largest dimension equal to 768 pixels, keeping the original aspect ratio.
The model predicts two classes: vertical and horizontal text lines.

## Evaluation results

The model achieves the following results:

| set   | class      | IoU   | F1    | AP@[.5] | AP@[.75] | AP@[.5,.95] |
| ----- | ---------- | ----: | ----: | ------: | -------: | ----------: |
| train | vertical   | 88.29 | 89.67 | 71.37   | 33.26    | 36.32       |
|       | horizontal | 69.81 | 81.35 | 91.73   | 36.62    | 45.67       |
| val   | vertical   | 73.01 | 75.13 | 46.02   | 4.99     | 15.58       |
|       | horizontal | 61.65 | 75.69 | 87.98   | 11.18    | 31.55       |
| test  | vertical   | 78.62 | 80.03 | 59.93   | 15.90    | 24.11       |
|       | horizontal | 63.59 | 76.49 | 95.93   | 24.18    | 41.45       |

## 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{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}
}
```