arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.16850eess.IVcs.CV
收藏

再论网格正则化的文档图像去畸变

Revisiting Document Image Dewarping by Grid Regularization

Wuhan University(武汉大学)

Xiangwei Jiang, Rujiao Long, Nan Xue, Zhibo Yang, Cong Yao, Gui-Song Xia

摘要:

针对文档数字化中文档图像的几何畸变问题,提出了一种文档图像去畸变的方法。我们没有设计一个更好的神经网络来近似输入和输出之间的光流场,而是从约束优化的角度考虑文本行和文档边界来追求最佳可读性。具体来说,我们提出的方法首先学习边界点和文本行中的像素,然后遵循最简单的观察,即在去扭曲后,水平和垂直方向上的边界和文本行都应该保持,以引入一种新的网格正则化方案。为了获得最终的正向映射去翘曲,我们用我们提出的网格正则化解决了一个优化问题。实验全面表明,我们提出的方法在可读性方面(字符错误率和编辑距离的指标)大大优于现有技术,同时在公开的DocUNet基准测试中保持最佳图像质量。

英文摘要:

This paper addresses the problem of document image dewarping, which aims at eliminating the geometric distortion in document images for document digitization. Instead of designing a better neural network to approximate the optical flow fields between the inputs and outputs, we pursue the best readability by taking the text lines and the document boundaries into account from a constrained optimization perspective. Specifically, our proposed method first learns the boundary points and the pixels in the text lines and then follows the most simple observation that the boundaries and text lines in both horizontal and vertical directions should be kept after dewarping to introduce a novel grid regularization scheme. To obtain the final forward mapping for dewarping, we solve an optimization problem with our proposed grid regularization. The experiments comprehensively demonstrate that our proposed approach outperforms the prior arts by large margins in terms of readability (with the metrics of Character Errors Rate and the Edit Distance) while maintaining the best image quality on the publicly-available DocUNet benchmark.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑