Presentation 2013-03-14
An OCR system with OCRopus for scientific documents containing mathematical expressions
Fumihiro FURUKORI, Takanori MIYAGISHI, Keiichiro SHIRAI, Masayuki OKAMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes installation of a mathematical formula recognition module into open source OCR system OCRopus, especially we consider the identification of inline formulas. Splitting a textline which includes math formulas into words and verifying them using a language model, we can distinguish the math formulas from words. Additionally, because the math formulas tend to have a variety of bounding boxes of symbols aspect ratios, we employ SVM using features associated with the bounding boxes so as to improve the accuracy of identification.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) OCR / OCRopus / Mathematical formula recognition
Paper # PRMU2012-193
Date of Issue

Conference Information
Committee PRMU
Conference Date 2013/3/7(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) An OCR system with OCRopus for scientific documents containing mathematical expressions
Sub Title (in English)
Keyword(1) OCR
Keyword(2) OCRopus
Keyword(3) Mathematical formula recognition
1st Author's Name Fumihiro FURUKORI
1st Author's Affiliation Faculty of Engineering, Shinshu Univ.()
2nd Author's Name Takanori MIYAGISHI
2nd Author's Affiliation Faculty of Engineering, Shinshu Univ.
3rd Author's Name Keiichiro SHIRAI
3rd Author's Affiliation Faculty of Engineering, Shinshu Univ.
4th Author's Name Masayuki OKAMOTO
4th Author's Affiliation Faculty of Engineering, Shinshu Univ.
Date 2013-03-14
Paper # PRMU2012-193
Volume (vol) vol.112
Number (no) 495
Page pp.pp.-
#Pages 5
Date of Issue