Presentation 2008-06-20
PDF Logical Structure Understanding for Document Template Generation
Masakazu FUJIO, Katsumi Marukawa, Hiroshi SHINJO, Takeshi NAGASAKI, Minenobu SEKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Simultaneous management of information in various paper and electronic documents is a serious problem because the complexity of the document structure would increases greatly. We have developed the system for integrating those information by analyzing layout patterns and text feature collocations in both document formats. In this paper, we introduce the application for extracting fixed text area and design, and variable text area, to construct reusable document templates.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) PDF / meta data / template / form structure analysis
Paper # DE2008-13,PRMU2008-31
Date of Issue

Conference Information
Committee DE
Conference Date 2008/6/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Data Engineering (DE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) PDF Logical Structure Understanding for Document Template Generation
Sub Title (in English)
Keyword(1) PDF
Keyword(2) meta data
Keyword(3) template
Keyword(4) form structure analysis
1st Author's Name Masakazu FUJIO
1st Author's Affiliation Hitachi Ltd., Central Research Laboratory()
2nd Author's Name Katsumi Marukawa
2nd Author's Affiliation Hitachi Ltd., Central Research Laboratory
3rd Author's Name Hiroshi SHINJO
3rd Author's Affiliation Hitachi Ltd., Central Research Laboratory
4th Author's Name Takeshi NAGASAKI
4th Author's Affiliation Hitachi Ltd., Central Research Laboratory
5th Author's Name Minenobu SEKI
5th Author's Affiliation Hitachi Ltd., Central Research Laboratory
Date 2008-06-20
Paper # DE2008-13,PRMU2008-31
Volume (vol) vol.108
Number (no) 93
Page pp.pp.-
#Pages 6
Date of Issue