johnlockejrr commited on
Commit
362f00c
1 Parent(s): 722e279

Upload 3 files

Browse files
Files changed (3) hide show
  1. README.md +58 -3
  2. model.pth +3 -0
  3. parameters.yml +10 -0
README.md CHANGED
@@ -1,3 +1,58 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: Doc-UFCN
3
+ license: mit
4
+ tags:
5
+ - Doc-UFCN
6
+ - PyTorch
7
+ - object-detection
8
+ - dla
9
+ - historical
10
+ - handwritten
11
+ metrics:
12
+ - IoU
13
+ - F1
14
+ - AP@.5
15
+ - AP@.75
16
+ - AP@[.5,.95]
17
+ pipeline_tag: image-segmentation
18
+ ---
19
+
20
+
21
+ # Doc-UFCN - Generic Samaritan manuscripts line detection
22
+
23
+ The generic Samaritan manuscripts line detection model predicts text lines from document images.
24
+
25
+ ## Model description
26
+
27
+ It has been trained on images with their largest dimension equal to 768 pixels, keeping the original aspect ratio.
28
+
29
+ ## How to use?
30
+
31
+ Please refer to the Doc-UFCN library page (https://pypi.org/project/doc-ufcn/) to use this model.
32
+
33
+ ## Cite us!
34
+
35
+ ```bibtex
36
+ @inproceedings{boillet2022,
37
+ author = {Boillet, Mélodie and Kermorvant, Christopher and Paquet, Thierry},
38
+ title = {{Robust Text Line Detection in Historical Documents: Learning and Evaluation Methods}},
39
+ booktitle = {{International Journal on Document Analysis and Recognition (IJDAR)}},
40
+ year = {2022},
41
+ month = Mar,
42
+ pages = {1433-2825},
43
+ doi = {10.1007/s10032-022-00395-7}
44
+ }
45
+ ```
46
+
47
+ ```bibtex
48
+ @inproceedings{boillet2020,
49
+ author = {Boillet, Mélodie and Kermorvant, Christopher and Paquet, Thierry},
50
+ title = {{Multiple Document Datasets Pre-training Improves Text Line Detection With
51
+ Deep Neural Networks}},
52
+ booktitle = {2020 25th International Conference on Pattern Recognition (ICPR)},
53
+ year = {2021},
54
+ month = Jan,
55
+ pages = {2134-2141},
56
+ doi = {10.1109/ICPR48806.2021.9412447}
57
+ }
58
+ ```
model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd9823c7ec645d45574950ab90b3bcaaade3eea9e02047f94826bcdb8292d85f
3
+ size 49220742
parameters.yml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ version: 0.0.2
3
+ parameters:
4
+ mean: [174, 161, 138]
5
+ std: [63, 61, 54]
6
+ min_cc: 50
7
+ classes:
8
+ - background
9
+ - text_line
10
+ input_size: 768