基于分割线和区域特征的页眉页脚判别方法  

Page Header and Footer Identification Method Based on Division Line and Region Characteristics

作　　者：刘高军[1] 刘妍妍[1] 付晓玲[1] 

机构地区：[1]北方工业大学信息工程学院,北京100144

出　　处：《北方工业大学学报》2013年第1期17-24,共8页Journal of North China University of Technology

基　　金："十一五"国家科技支撑平台重点项目(2009BA171B02)

摘　　要：针对基于OCR和版面分析的应用中,需将页眉页脚与主体部分分离并加以单独处理的需求,在分析主流书籍、杂志的页眉页脚特征基础上,提出了分割线探测结合区域特征的页眉页脚判别算法.本算法可以有效地检测出有分割线的页眉、无分割线的左对齐和右对齐页眉和一般的页脚.经实验验证,所提出的算法具有一定的有效性和通用性.In the application based on OCR （Optical Character Recognition） and layout analysis, it is needed to distinguish the page header and footer from the body in documents and process them separately. On the basis of the analysis of the characteristics of the page header and footer of mainstream books and magazines, a page header and footer identification method, combining the division line and region characteristics, is put forward. The method can effectively detect page header with devision line, left-aligning page header and right-aligning pager header without devision line and general page footer. The experimental results prove the effectiveness and generality of the proposed method.

关 键 词：光学字符识别(OCR) 版面分析 页眉 页脚 分割线 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]