Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,9 @@ The model and its training code has been mainly taken from: [Tensorpack](https:/
|
|
| 13 |
|
| 14 |
Regarding the dataset, please check: [Xu Zhong et. all. - Image-based table recognition: data, model, and evaluation](https://arxiv.org/abs/1911.10683).
|
| 15 |
|
|
|
|
|
|
|
|
|
|
| 16 |
The code has been adapted so that it can be used in a **deep**doctection pipeline.
|
| 17 |
|
| 18 |
## How this model can be used
|
|
|
|
| 13 |
|
| 14 |
Regarding the dataset, please check: [Xu Zhong et. all. - Image-based table recognition: data, model, and evaluation](https://arxiv.org/abs/1911.10683).
|
| 15 |
|
| 16 |
+
The model has been trained on detecting rows and columns for tables. As rows and column bounding boxes are not a priori an element of the annotations they are
|
| 17 |
+
calculated using the bounding boxes of the cells and the intrinsic structure of the enclosed HTML.
|
| 18 |
+
|
| 19 |
The code has been adapted so that it can be used in a **deep**doctection pipeline.
|
| 20 |
|
| 21 |
## How this model can be used
|