Geometric Rectification of Document Images using Adversarial Gated Unwarping Network
Xiyan Liu1,2; Gaofeng Meng1,2; Bin Fan1,3; Shiming Xiang1,2; Chunhong Pan1
发表期刊Pattern Recognition
2020
卷号108期号:108页码:1-13
摘要

Document images captured in natural scenes with a hand-held camera often suffer from geometric distortions and cluttered backgrounds. In this paper, we propose a simple yet efficient deep model named Adversarial Gated Unwarping Network (AGUN) to rectify these images. In this model, the rectification task is recast as a dense grid prediction problem. We thereby develop a pyramid encoder-decoder architecture to predict the unwarping grid at multiple resolutions in a coarse-to-fine fashion. Based on the observation that the structural visual cues, e.g., text-lines, text blocks, lines in tables, which are critical for the estimation of unwarping mapping, are non-uniformly distributed in the images, three gated modules are introduced to guide the network focusing on these informative cues rather than other interferences such as blank areas and complex backgrounds. To generate more visually pleasing rectification results, we further adopt adversarial training mechanism to implicitly constrain the unwarping grid estimation. Our model can rectify arbitrarily distorted document images with complicated page layouts and cluttered backgrounds. Experiments on the public benchmark dataset and the synthetic dataset demonstrate that our approach outperforms the state-of-the-art methods in terms of OCR accuracy and several widely used quantitative evaluation metrics.

关键词Distorted document image Geometric rectification Gated module Deep learning
收录类别SCI
语种英语
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/46641
专题模式识别国家重点实验室_先进时空数据分析与学习
通讯作者Gaofeng Meng
作者单位1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
3.School of Automation and Electrical Engineering, University of Science and Technology Beijing
第一作者单位模式识别国家重点实验室
通讯作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
Xiyan Liu,Gaofeng Meng,Bin Fan,et al. Geometric Rectification of Document Images using Adversarial Gated Unwarping Network[J]. Pattern Recognition,2020,108(108):1-13.
APA Xiyan Liu,Gaofeng Meng,Bin Fan,Shiming Xiang,&Chunhong Pan.(2020).Geometric Rectification of Document Images using Adversarial Gated Unwarping Network.Pattern Recognition,108(108),1-13.
MLA Xiyan Liu,et al."Geometric Rectification of Document Images using Adversarial Gated Unwarping Network".Pattern Recognition 108.108(2020):1-13.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
1-s2.0-S003132032030(7916KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Xiyan Liu]的文章
[Gaofeng Meng]的文章
[Bin Fan]的文章
百度学术
百度学术中相似的文章
[Xiyan Liu]的文章
[Gaofeng Meng]的文章
[Bin Fan]的文章
必应学术
必应学术中相似的文章
[Xiyan Liu]的文章
[Gaofeng Meng]的文章
[Bin Fan]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 1-s2.0-S0031320320303794-main.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。