diff --git a/README.md b/README.md index 5a964ef..6ba2436 100755 --- a/README.md +++ b/README.md @@ -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:youngmin.baek@navercorp.com), 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. teaser @@ -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) ```