Hybrid Page Segmentation with Efficient Whitespace Rectangles Extraction and Grouping

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	Hybrid Page Segmentation with Efficient Whitespace Rectangles Extraction and Grouping
	Chen, Kai; Yin, Fei; Liu, Cheng-Lin
	2013-08
会议名称	2013 12TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR)
会议录名称	International Conference on Document Analysis and Recognition (ICDAR)
页码	958-962
会议日期	2013-8
会议地点	美国华盛顿
摘要	Page segmentation is still a challenging problem due to the large variety of document layouts. Methods examining both foreground and background regions are among the most effective to solve this problem. However, their performance is influenced by the implementation of two key steps: the extraction and selection of background regions, and the grouping of background regions into separators. This paper proposes an efficient hybrid method for page segmentation. The method extracts whitespace rectangles based on connected component analysis, and filters whitespace rectangles progressively incorporating foreground and background information such that the remaining rectangles are likely to form column separators. Experimental results on the ICDAR2009 page segmentation competition test set demonstrate the effectiveness and superiority of the proposed method.
关键词	Page Segmentation Whitespace Rectangles Extraction Whitespace Rectangles Grouping
收录类别	EI
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/4377
专题	多模态人工智能系统全国重点实验室_模式分析与学习
通讯作者	Chen, Kai
作者单位	中科院自动化研究所
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Chen, Kai,Yin, Fei,Liu, Cheng-Lin. Hybrid Page Segmentation with Efficient Whitespace Rectangles Extraction and Grouping[C],2013:958-962.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Hybrid_Page_Chen.pdf（750KB）	会议论文		开放获取	CC BY-NC-SA	浏览