ForCenNet: Foreground-Centric Network for Document Image Rectification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915410921652224 |
|---|---|
| author | Cai, Peng Li, Qiang Yang, Kaicheng Guo, Dong Li, Jia Zhou, Nan An, Xiang Yang, Ninghua Deng, Jiankang |
| author_facet | Cai, Peng Li, Qiang Yang, Kaicheng Guo, Dong Li, Jia Zhou, Nan An, Xiang Yang, Ninghua Deng, Jiankang |
| contents | Document image rectification aims to eliminate geometric deformation in photographed documents to facilitate text recognition. However, existing methods often neglect the significance of foreground elements, which provide essential geometric references and layout information for document image correction. In this paper, we introduce Foreground-Centric Network (ForCenNet) to eliminate geometric distortions in document images. Specifically, we initially propose a foreground-centric label generation method, which extracts detailed foreground elements from an undistorted image. Then we introduce a foreground-centric mask mechanism to enhance the distinction between readable and background regions. Furthermore, we design a curvature consistency loss to leverage the detailed foreground labels to help the model understand the distorted geometric distribution. Extensive experiments demonstrate that ForCenNet achieves new state-of-the-art on four real-world benchmarks, such as DocUNet, DIR300, WarpDoc, and DocReal. Quantitative analysis shows that the proposed method effectively undistorts layout elements, such as text lines and table borders. The resources for further comparison are provided at https://github.com/caipeng328/ForCenNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19804 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ForCenNet: Foreground-Centric Network for Document Image Rectification Cai, Peng Li, Qiang Yang, Kaicheng Guo, Dong Li, Jia Zhou, Nan An, Xiang Yang, Ninghua Deng, Jiankang Computer Vision and Pattern Recognition Document image rectification aims to eliminate geometric deformation in photographed documents to facilitate text recognition. However, existing methods often neglect the significance of foreground elements, which provide essential geometric references and layout information for document image correction. In this paper, we introduce Foreground-Centric Network (ForCenNet) to eliminate geometric distortions in document images. Specifically, we initially propose a foreground-centric label generation method, which extracts detailed foreground elements from an undistorted image. Then we introduce a foreground-centric mask mechanism to enhance the distinction between readable and background regions. Furthermore, we design a curvature consistency loss to leverage the detailed foreground labels to help the model understand the distorted geometric distribution. Extensive experiments demonstrate that ForCenNet achieves new state-of-the-art on four real-world benchmarks, such as DocUNet, DIR300, WarpDoc, and DocReal. Quantitative analysis shows that the proposed method effectively undistorts layout elements, such as text lines and table borders. The resources for further comparison are provided at https://github.com/caipeng328/ForCenNet. |
| title | ForCenNet: Foreground-Centric Network for Document Image Rectification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.19804 |