mboillet commited on
Commit
0bdb94c
1 Parent(s): 21f246a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -5
README.md CHANGED
@@ -16,7 +16,6 @@ metrics:
16
  pipeline_tag: image-segmentation
17
  ---
18
 
19
-
20
  # Doc-UFCN - Generic page detection
21
 
22
  The generic page detection model predicts single pages from document images.
@@ -30,20 +29,20 @@ It has been trained on images with their largest dimension equal to 768 pixels,
30
 
31
  The model achieves the following results:
32
 
33
- | | set | IoU | F1 | AP@[.5] | AP@[.75] | AP@[.5,.95] |
34
- | ----- | -------- | ----: | ----: | ------: | -------: | ----------: |
35
  | HOME | test | 93.92 | 95.84 | 98.98 | 98.98 | 97.61 |
36
  | Horae | test | 96.68 | 98.31 | 99.76 | 98.49 | 98.08 |
37
  | Horae | test-300 | 95.66 | 97.27 | 98.87 | 98.45 | 97.38 |
38
 
39
  ## How to use?
40
 
41
- Please refer to the Doc-UFCN library page (https://pypi.org/project/doc-ufcn/) to use this model.
42
 
43
  ## Cite us!
44
 
45
  ```bibtex
46
- @inproceedings{boillet2020,
47
  author = {Boillet, Mélodie and Kermorvant, Christopher and Paquet, Thierry},
48
  title = {{Multiple Document Datasets Pre-training Improves Text Line Detection With
49
  Deep Neural Networks}},
 
16
  pipeline_tag: image-segmentation
17
  ---
18
 
 
19
  # Doc-UFCN - Generic page detection
20
 
21
  The generic page detection model predicts single pages from document images.
 
29
 
30
  The model achieves the following results:
31
 
32
+ | dataset | set | IoU | F1 | AP@[.5] | AP@[.75] | AP@[.5,.95] |
33
+ | :----- | :------- | ----: | ----: | ------: | -------: | ----------: |
34
  | HOME | test | 93.92 | 95.84 | 98.98 | 98.98 | 97.61 |
35
  | Horae | test | 96.68 | 98.31 | 99.76 | 98.49 | 98.08 |
36
  | Horae | test-300 | 95.66 | 97.27 | 98.87 | 98.45 | 97.38 |
37
 
38
  ## How to use?
39
 
40
+ Please refer to the [Doc-UFCN library page](https://pypi.org/project/doc-ufcn/) to use this model.
41
 
42
  ## Cite us!
43
 
44
  ```bibtex
45
+ @inproceedings{doc_ufcn2021,
46
  author = {Boillet, Mélodie and Kermorvant, Christopher and Paquet, Thierry},
47
  title = {{Multiple Document Datasets Pre-training Improves Text Line Detection With
48
  Deep Neural Networks}},