Skip to content

Commit

Permalink
update for rectify parameter
Browse files Browse the repository at this point in the history
  • Loading branch information
fcakyon committed Mar 23, 2020
1 parent 7bee180 commit afb38f6
Showing 1 changed file with 17 additions and 17 deletions.
34 changes: 17 additions & 17 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,14 +2,14 @@
![CI](https://github.com/fcakyon/craft-text-detector/workflows/CI/badge.svg)

## CRAFT: Character-Region Awareness For Text detection
Packaged Version of the Official Pytorch implementation of CRAFT text detector | [Paper](https://arxiv.org/abs/1904.01941) | [Supplementary](https://youtu.be/HI8MzpY8KMI) |
Packaged Version of the Official Pytorch implementation of CRAFT text detector | [Paper](https://arxiv.org/abs/1904.01941) | [Supplementary](https://youtu.be/HI8MzpY8KMI) |

**[Youngmin Baek](mailto:[email protected]), Bado Lee, Dongyoon Han, Sangdoo Yun, Hwalsuk Lee.**

**Package maintainer: Fatih Cagatay Akyon**

### Overview
PyTorch implementation for CRAFT text detector that effectively detect text area by exploring each character region and affinity between characters. The bounding box of texts are obtained by simply finding minimum bounding rectangles on binary map after thresholding character region and affinity scores.
PyTorch implementation for CRAFT text detector that effectively detect text area by exploring each character region and affinity between characters. The bounding box of texts are obtained by simply finding minimum bounding rectangles on binary map after thresholding character region and affinity scores.

<img width="1000" alt="teaser" src="./figures/craft_example.gif">

Expand Down Expand Up @@ -54,26 +54,26 @@ craft_net = craft.load_craftnet_model()

# perform prediction
bboxes, polys, heatmap = craft.get_prediction(image=image,
craft_net=craft_net,
refine_net=refine_net,
text_threshold=0.7,
link_threshold=0.4,
low_text=0.4,
cuda=True,
show_time=True)
craft_net=craft_net,
refine_net=refine_net,
text_threshold=0.7,
link_threshold=0.4,
low_text=0.4,
cuda=True,
show_time=True)

# export detected text regions
craft.export_detected_regions(image_path=image_path,
image=image,
regions=polys,
output_dir=output_dir)
image=image,
regions=polys,
output_dir=output_dir,
rectify=rectify)

# export heatmap, detection points, box visualization
craft.export_extra_results(image_path=image_path,
image=image,
image=image,
regions=polys,
heatmap=heatmap,
output_dir=output_dir,
smooth_contour=True)
output_dir=output_dir)
```

0 comments on commit afb38f6

Please sign in to comment.