Presentation 2004/9/3
Information Extraction from Various Document Formats Based on PDL Analysis
Takashi Hirano, Taizo Kameshiro, Yasuhiro Okada, Fumio Yoda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a document analysis method which extracts text information form various document format files. In this method, a PDL (Page Description Language) data file is generated by doing dummy printing process of a document file. In the PDL data analysis, while extracting the text from inside of the PDL data, character recognition process for images is carried out. It allows text extraction without extraction loss from various document files, such as electronic document, image document, and CAD data. The design of this method is presented and experimental results are discussed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # PRMU2004-66
Date of Issue

Conference Information
Committee PRMU
Conference Date 2004/9/3(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Information Extraction from Various Document Formats Based on PDL Analysis
Sub Title (in English)
Keyword(1)
1st Author's Name Takashi Hirano
1st Author's Affiliation Mitsubishi Electric Corporation, Information Technology R&D Center()
2nd Author's Name Taizo Kameshiro
2nd Author's Affiliation Mitsubishi Electric Corporation, Information Technology R&D Center
3rd Author's Name Yasuhiro Okada
3rd Author's Affiliation Mitsubishi Electric Corporation, Information Technology R&D Center
4th Author's Name Fumio Yoda
4th Author's Affiliation Mitsubishi Electric Corporation, Information Technology R&D Center
Date 2004/9/3
Paper # PRMU2004-66
Volume (vol) vol.104
Number (no) 290
Page pp.pp.-
#Pages 6
Date of Issue