CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913277101998080 |
|---|---|
| author | Zhao, Xi Feng, Wei Zhang, Zheng Lv, Jingjing Zhu, Xin Lin, Zhangang Hu, Jinghe Shao, Jingping |
| author_facet | Zhao, Xi Feng, Wei Zhang, Zheng Lv, Jingjing Zhu, Xin Lin, Zhangang Hu, Jinghe Shao, Jingping |
| contents | Recently, segmentation-based methods are quite popular in scene text detection, which mainly contain two steps: text kernel segmentation and expansion. However, the segmentation process only considers each pixel independently, and the expansion process is difficult to achieve a favorable accuracy-speed trade-off. In this paper, we propose a Context-aware and Boundary-guided Network (CBN) to tackle these problems. In CBN, a basic text detector is firstly used to predict initial segmentation results. Then, we propose a context-aware module to enhance text kernel feature representations, which considers both global and local contexts. Finally, we introduce a boundary-guided module to expand enhanced text kernels adaptively with only the pixels on the contours, which not only obtains accurate text boundaries but also keeps high speed, especially on high-resolution output maps. In particular, with a lightweight backbone, the basic detector equipped with our proposed CBN achieves state-of-the-art results on several popular benchmarks, and our proposed CBN can be plugged into several segmentation-based methods. Code is available at https://github.com/XiiZhao/cbn.pytorch. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_02340 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detection Zhao, Xi Feng, Wei Zhang, Zheng Lv, Jingjing Zhu, Xin Lin, Zhangang Hu, Jinghe Shao, Jingping Computer Vision and Pattern Recognition Recently, segmentation-based methods are quite popular in scene text detection, which mainly contain two steps: text kernel segmentation and expansion. However, the segmentation process only considers each pixel independently, and the expansion process is difficult to achieve a favorable accuracy-speed trade-off. In this paper, we propose a Context-aware and Boundary-guided Network (CBN) to tackle these problems. In CBN, a basic text detector is firstly used to predict initial segmentation results. Then, we propose a context-aware module to enhance text kernel feature representations, which considers both global and local contexts. Finally, we introduce a boundary-guided module to expand enhanced text kernels adaptively with only the pixels on the contours, which not only obtains accurate text boundaries but also keeps high speed, especially on high-resolution output maps. In particular, with a lightweight backbone, the basic detector equipped with our proposed CBN achieves state-of-the-art results on several popular benchmarks, and our proposed CBN can be plugged into several segmentation-based methods. Code is available at https://github.com/XiiZhao/cbn.pytorch. |
| title | CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2212.02340 |