Commit
•
c081ac5
1
Parent(s):
95b57e2
Add description to README
Browse files
README.md
CHANGED
|
@@ -1,10 +1,67 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
|
|
|
| 3 |
|
| 4 |
-
|
| 5 |
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: PyLaia
|
| 3 |
+
license: mit
|
| 4 |
+
tags:
|
| 5 |
+
- PyLaia
|
| 6 |
+
- PyTorch
|
| 7 |
+
- Handwritten text recognition
|
| 8 |
+
metrics:
|
| 9 |
+
- CER
|
| 10 |
+
- WER
|
| 11 |
+
language:
|
| 12 |
+
- 'lat'
|
| 13 |
+
---
|
| 14 |
|
| 15 |
+
# HOME-Alcar and Himanis handwritten text recognition
|
| 16 |
|
| 17 |
+
This model performs Handwritten Text Recognition in Latin. It was was developed during the [HUGIN-MUNIN project](https://hugin-munin-project.github.io/).
|
| 18 |
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
The model has been trained using the PyLaia library on the [NorHand](https://zenodo.org/record/5600884) document images.
|
| 22 |
+
Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
|
| 23 |
+
|
| 24 |
+
## Evaluation results
|
| 25 |
+
|
| 26 |
+
The model achieves the following results:
|
| 27 |
+
|
| 28 |
+
Himanis:
|
| 29 |
+
|
| 30 |
+
| set | CER (%) | WER (%) | support |
|
| 31 |
+
| ----- | ---------- | --------- | --------- |
|
| 32 |
+
| train | 5.31 | 17.47 | 18503 |
|
| 33 |
+
| val | 10.37 | 27.63 | 2367 |
|
| 34 |
+
| test | 9.87 | 28.27 | 2241 |
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
Alcar:
|
| 38 |
+
|
| 39 |
+
| set | CER (%) | WER (%) | support |
|
| 40 |
+
| ----- | ---------- | --------- | --------- |
|
| 41 |
+
| train | 4.74 | 17.29 | 59969 |
|
| 42 |
+
| val | 7.82 | 23.67 | 7905 |
|
| 43 |
+
| test | 8.34 | 24.57 | 6932 |
|
| 44 |
+
|
| 45 |
+
## How to use
|
| 46 |
+
|
| 47 |
+
Please refer to the PyLaia library page (https://pypi.org/project/pylaia/) to use this model.
|
| 48 |
+
|
| 49 |
+
# Cite us!
|
| 50 |
+
|
| 51 |
+
```bibtex
|
| 52 |
+
@inproceedings{10.1007/978-3-031-06555-2_27,
|
| 53 |
+
author = {Maarand, Martin and Beyer, Yngvil and K\r{a}sen, Andre and Fosseide, Knut T. and Kermorvant, Christopher},
|
| 54 |
+
title = {A Comprehensive Comparison of Open-Source Libraries for Handwritten Text Recognition in Latin},
|
| 55 |
+
year = {2022},
|
| 56 |
+
isbn = {978-3-031-06554-5},
|
| 57 |
+
publisher = {Springer-Verlag},
|
| 58 |
+
address = {Berlin, Heidelberg},
|
| 59 |
+
url = {https://doi.org/10.1007/978-3-031-06555-2_27},
|
| 60 |
+
doi = {10.1007/978-3-031-06555-2_27},
|
| 61 |
+
booktitle = {Document Analysis Systems: 15th IAPR International Workshop, DAS 2022, La Rochelle, France, May 22–25, 2022, Proceedings},
|
| 62 |
+
pages = {399–413},
|
| 63 |
+
numpages = {15},
|
| 64 |
+
keywords = {Latin language, Open-source, Handwriting recognition},
|
| 65 |
+
location = {La Rochelle, France}
|
| 66 |
+
}
|
| 67 |
+
```
|