CASIA OpenIR  > 毕业生  > 硕士学位论文
Thesis Advisor刘迎建
Degree Grantor中国科学院自动化研究所
Place of Conferral中国科学院自动化研究所
Degree Discipline模式识别与智能系统
Abstract表格处理是文本分析和处理中一个重要的组成部分,其研究领域大致可分 成两类:表格版面分析和填入数据提取。本文的研究主要集中在表格版面分析 和表格自动处理系统上。 本文介绍了一种基于直线提取和补全的表格分析方法。先使用一种游程跟 踪的直线提取算法求得表格线,同时对表格进行倾斜校正。然后根据表格特性 调整表格线,再从表格线得到表格特征点,最后建立规则通过对表格线的补全 来求得表格结构的行单元描述。此方法取得了良好的实验结果。 本论文还介绍了一个工商局表格处理系统。此系统由表格描述、表格识别、 表格注册、数据提取和识别等步骤组成。该系统在济南和珠海工商局得到成功 应用。
Other AbstractForm processing is an important part in the research of document analysis and recognition. There are mainly two research areas in form processing: form layout analysis and filled-in data extraction. In this paper, our research work focuses on form layout analysis and automatic form processing system. This paper presents a form analysis method based on line extraction and completion. We use a run-length tracking algorithm to extract form lines first, and in the same time the skew angle is detected. Lines are adjusted according to the characteristic of form. Then all critical points are calculated from which tbrm cell description of the form can be derived based on some rules to complete the form lines. This method shows good result in experiment. This paper also describes an automatic form processing system for Business Administration Office. The system consists of form description, form classification, form registration, data extraction and recognition. This system has been successfully applied in Jinan and Zhuhai Business Administration Office.
Other Identifier557
Document Type学位论文
Recommended Citation
GB/T 7714
章海涛. 表格分析和自动处理[D]. 中国科学院自动化研究所. 中国科学院自动化研究所,2000.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[章海涛]'s Articles
Baidu academic
Similar articles in Baidu academic
[章海涛]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[章海涛]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.