Related papers: Fourier Document Restoration for Robust Document Dewarping and Recognition

Fourier Document Restoration for Robust Document Dewarping and Recognition

URL: http://arxiv.org/abs/2203.09910v1
Date: Fri, 18 Mar 2022 12:39:31 GMT
Title: Fourier Document Restoration for Robust Document Dewarping and Recognition
Authors: Chuhui Xue, Zichen Tian, Fangneng Zhan, Shijian Lu, Song Bai
Abstract summary: This paper presents FDRNet, a Fourier Document Restoration Network that can restore documents with different distortions. It dewarps documents by a flexible Thin-Plate Spline transformation which can handle various deformations effectively without requiring deformation annotations in training. It outperforms the state-of-the-art by large margins on both dewarping and text recognition tasks.
Score: 73.44057202891011
License: http://creativecommons.org/publicdomain/zero/1.0/
Abstract: State-of-the-art document dewarping techniques learn to predict 3-dimensional information of documents which are prone to errors while dealing with documents with irregular distortions or large variations in depth. This paper presents FDRNet, a Fourier Document Restoration Network that can restore documents with different distortions and improve document recognition in a reliable and simpler manner. FDRNet focuses on high-frequency components in the Fourier space that capture most structural information but are largely free of degradation in appearance. It dewarps documents by a flexible Thin-Plate Spline transformation which can handle various deformations effectively without requiring deformation annotations in training. These features allow FDRNet to learn from a small amount of simply labeled training images, and the learned model can dewarp documents with complex geometric distortion and recognize the restored texts accurately. To facilitate document restoration research, we create a benchmark dataset consisting of over one thousand camera documents with different types of geometric and photometric distortion. Extensive experiments show that FDRNet outperforms the state-of-the-art by large margins on both dewarping and text recognition tasks. In addition, FDRNet requires a small amount of simply labeled training data and is easy to deploy.