mirrors/PaddleOCR
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/PaddleOCR.git synced 2025-06-03 21:53:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

add CT to algorithm overview (#8998)

Browse Source 
* add ct to model zoo

* refine details
This commit is contained in:
huangjun12 2023-02-10 11:08:40 +08:00 committed by GitHub
parent 68099c2d5b
commit 7c81d482e9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
doc/doc_ch/algorithm_overview.md
View File

@ -32,6 +32,7 @@ PaddleOCR将**持续新增**支持OCR领域前沿算法与模型，**欢迎广
- [x] [PSENet](./algorithm_det_psenet.md)
- [x] [FCENet](./algorithm_det_fcenet.md)
- [x] [DRRG](./algorithm_det_drrg.md)
- [x] [CT](./algorithm_det_ct.md)
在ICDAR2015文本检测公开数据集上，算法效果如下：
@ -51,6 +52,7 @@ PaddleOCR将**持续新增**支持OCR领域前沿算法与模型，**欢迎广
|模型|骨干网络|precision|recall|Hmean|下载链接|
| --- | --- | --- | --- | --- | --- |
|SAST|ResNet50_vd|89.63%|78.44%|83.66%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)|
|CT|ResNet18_vd|88.68%|81.70%|85.05%|[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r18_ct_train.tar)|
在CTW1500文本检测公开数据集上，算法效果如下：

2
doc/doc_en/algorithm_overview_en.md
View File

@ -30,6 +30,7 @@ Supported text detection algorithms (Click the link to get the tutorial):
- [x] [PSENet](./algorithm_det_psenet_en.md)
- [x] [FCENet](./algorithm_det_fcenet_en.md)
- [x] [DRRG](./algorithm_det_drrg_en.md)
- [x] [CT](./algorithm_det_ct_en.md)
On the ICDAR2015 dataset, the text detection result is as follows:
@ -49,6 +50,7 @@ On Total-Text dataset, the text detection result is as follows:
|Model|Backbone|Precision|Recall|Hmean|Download link|
| --- | --- | --- | --- | --- | --- |
|SAST|ResNet50_vd|89.63%|78.44%|83.66%|[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)|
|CT|ResNet18_vd|88.68%|81.70%|85.05%|[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r18_ct_train.tar)|
On CTW1500 dataset, the text detection result is as follows: