Mask R-CNN with Pyramid Attention Network for Scene Text Detection

Zhida Huang, Zhuoyao Zhong, Lei Sun, Qiang Huo

WACV 2019 pp. 764-772

doi:10.1109/WACV.2019.00086 /wacv/2019/huang2019wacv-mask/

Abstract

In this paper, we present a new Mask R-CNN based text detection approach which can robustly detect multi-oriented and curved text from natural scene images in a unified manner. To enhance the feature representation ability of Mask R-CNN for text detection tasks, we propose to use the Pyramid Attention Network (PAN) as a new backbone network of Mask R-CNN. Experiments demonstrate that PAN can suppress false alarms caused by text-like backgrounds more effectively. Our proposed approach has achieved superior performance on both multi-oriented (ICDAR-2015, ICDAR-2017 MLT) and curved (SCUT-CTW1500) text detection benchmark tasks by only using single-scale and single-model testing.

PDF WACV Semantic Scholar

Cite

Text

Huang et al. "Mask R-CNN with Pyramid Attention Network for Scene Text Detection." IEEE/CVF Winter Conference on Applications of Computer Vision, 2019. doi:10.1109/WACV.2019.00086

Markdown

[Huang et al. "Mask R-CNN with Pyramid Attention Network for Scene Text Detection." IEEE/CVF Winter Conference on Applications of Computer Vision, 2019.](https://mlanthology.org/wacv/2019/huang2019wacv-mask/) doi:10.1109/WACV.2019.00086

BibTeX

@inproceedings{huang2019wacv-mask,
  title     = {{Mask R-CNN with Pyramid Attention Network for Scene Text Detection}},
  author    = {Huang, Zhida and Zhong, Zhuoyao and Sun, Lei and Huo, Qiang},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2019},
  pages     = {764-772},
  doi       = {10.1109/WACV.2019.00086},
  url       = {https://mlanthology.org/wacv/2019/huang2019wacv-mask/}
}