PDF文档表格信息的识别与提取  

Recognition and Extraction of Table Information from PDF Documents

作　　者：田翠华 张一平 胡志钢 高静敏 李西雨 TIAN Cuihua;ZHANG Yiping;HU Zhigang;GAO Jingmin;LI Xiyu(School of Computer & Information Engineering,Xiamen University of Technology,Xiamen 361024,China)

机构地区：[1]厦门理工学院计算机与信息工程学院,福建厦门361024

出　　处：《厦门理工学院学报》2020年第3期70-76,共7页Journal of Xiamen University of Technology

基　　金：厦门市科技计划项目(3502Z20193058);厦门理工学院优质研究生课程及案例库建设项目(YG20190303);厦门理工学院创新创业实验班校企合作项目(2019SYB07)。

摘　　要：为编辑PDF文档中的表格信息,设计一种基于Python平台的,包含文件选取与文件转换两大功能模块的信息提取软件。该软件利用Python内置库,针对PDF中不同表格的结构设计算法,识别表格内的文字信息与表格结构,将得到的表格结构还原至Word与Excel文档中,文字信息同样复原至对应单元格内。实验表明:开发的软件完整快速地提取了PDF中的表格信息,并将其转化为易于编辑的Excel和Word文档,达到了预期目的;其转换速度与收费软件WPS相当,转换速度明显快于其他免费转换软件;识别精确度与迅捷PDF转换器、Smallpdf等相比有所提高。An information extraction software to edit the table information in PDF documents was designed on the Python platform,which contains modules of file selection and file conversion.The software uses the Python built-in library to design algorithms for structures of different tables in PDF,recognizes the text information and table structure in the table,and restores the obtained table structure to Word documents or Excel documents and the text information to the corresponding cells.Experiments show that the software developed extracts table information from PDF documents completely and quickly,and converts it into easy-to-edit Excel and Word documents,achieving the expected results.It has a conversion speed equivalent to that of paid software WPS and significantly faster than those of other free conversion software,and its recognition accuracy is better than Xunjiepdf,Smallpdf and the likes.

关 键 词：PDF文档 表格信息 信息识别 信息提取 Python开发平台 

分 类 号：TP317[自动化与计算机技术—计算机软件与理论]