中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 遥感图像处理团队
Baselines Extraction from Curved Document Images via Slope Fields Recovery

文献类型：期刊论文

作者Meng, Gaofeng2; Pan, Chunhong2; Xiang, Shiming2; Wu, Ying1
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2020-04-01
卷号42期号:4页码:793-808
关键词Estimation Image segmentation Layout Distortion Strips Image quality Degradation Document image processing curved baselines extraction slope fields recovery geometric distortion rectification
ISSN号0162-8828
DOI10.1109/TPAMI.2018.2886900
通讯作者Xiang, Shiming(smxiang@nlpr.ia.ac.cn)
英文摘要Baselines estimation is a critical preprocessing step for many tasks of document image processing and analysis. The problem is very challenging due to arbitrarily complicated page layouts and various types of image quality degradations. This paper proposes a method based on slope fields recovery for curved baseline extraction from a distorted document image captured by a hand-held camera. Our method treats the curved baselines as the solution curves of an ordinary differential equation defined on a slope field. By assuming the page shape is a smooth and developable surface, we investigate a type of intrinsic geometric constraints of baselines to estimate the latent slope field. The curved baselines are finally obtained by solving an ordinary differential equation through the Euler method. Unlike the traditional text-lines based methods, our method is free from text-lines detection and segmentation. It can exploit multiple visual cues other than horizontal text-lines available in images for baselines extraction and is quite robust to document scripts, various types of image quality degradation (e.g., image distortion, blur and non-uniform illumination), large areas of non-textual objects and complex page layouts. Extensive experiments on synthetic and real-captured document images are implemented to evaluate the performance of the proposed method.
WOS关键词TEXT ; SEGMENTATION ; RECTIFICATION ; ROBUST ; SET
资助项目National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[61573352] ; National Natural Science Foundation of China[61802407] ; US National Science Foundation[IIS1217302] ; US National Science Foundation[IIS-1619078] ; Army Research Office ARO[W911NF-16-1-0138]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000526541100003
出版者IEEE COMPUTER SOC
资助机构National Natural Science Foundation of China ; US National Science Foundation ; Army Research Office ARO
源URL[http://ir.ia.ac.cn/handle/173211/38830]  
专题自动化研究所_模式识别国家重点实验室_遥感图像处理团队
通讯作者Xiang, Shiming
作者单位1.Northwestern Univ, 2145 Sheridan Rd, Evanston, IL 60208 USA
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Zhongguancun East Rd 95, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Meng, Gaofeng,Pan, Chunhong,Xiang, Shiming,et al. Baselines Extraction from Curved Document Images via Slope Fields Recovery[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2020,42(4):793-808.
APA Meng, Gaofeng,Pan, Chunhong,Xiang, Shiming,&Wu, Ying.(2020).Baselines Extraction from Curved Document Images via Slope Fields Recovery.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,42(4),793-808.
MLA Meng, Gaofeng,et al."Baselines Extraction from Curved Document Images via Slope Fields Recovery".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 42.4(2020):793-808.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。