Presentation 2006-03-16
A Study on Character Recognition Error Correction Method for Mathematical Formulae using Higher Level Information
Yusuke TAKIGUCHI, Minoru OKADA, Yasuji MIYAKE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper we propose a method for correcting character recognition errors at the higher level recognition step of the mathematical formulae recognition and understanding system. The system consists of two-level recognition steps: the low level recognition including character recognition, and the higher level recognition including layout recognition. We apply the layout information recognized in the latter step, and character recognition errors are corrected by using two sources of information. One is by some keywords such as mathematical function names, and the other is based on a cost tree and co-occurrence probabilities between symbols. Availability of the proposed method is indicated by some experimental results, and the character recognition rate raised from 79.8% to 90.2% and the formula recognition rate raised from 5.8% to 41.1% are confirmed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) mathematical formulae recognition / higher level information / character recognition error correction / cost tree / co-occurrence probability
Paper # PRMU2005-248
Date of Issue

Conference Information
Committee PRMU
Conference Date 2006/3/9(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) A Study on Character Recognition Error Correction Method for Mathematical Formulae using Higher Level Information
Sub Title (in English)
Keyword(1) mathematical formulae recognition
Keyword(2) higher level information
Keyword(3) character recognition error correction
Keyword(4) cost tree
Keyword(5) co-occurrence probability
1st Author's Name Yusuke TAKIGUCHI
1st Author's Affiliation Graduate School of Information, Production and Systems, Waseda University()
2nd Author's Name Minoru OKADA
2nd Author's Affiliation Graduate School of Information, Production and Systems, Waseda University
3rd Author's Name Yasuji MIYAKE
3rd Author's Affiliation College of Engineering, Chubu University
Date 2006-03-16
Paper # PRMU2005-248
Volume (vol) vol.105
Number (no) 673
Page pp.pp.-
#Pages 6
Date of Issue