Presentation 2002/3/7
Bigram-based Post-processing for On-line Handwriting Recognition Using Correctness Evaluation
Hiromitsu KAWAJIRI, Akira NAKAMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) An approach to bigram-based linguistic processing for on-tine handwriting text recognition is described. A probability of correctness for each recognition result is derived from a feature set which consists of bigram probabilities and recognition scores. Using the probability of correctness, the number of candidates accepted to the post-processing step and the weight value balancing recognition scores with bigram scores are adaptively controlled. The proposed method is evaluated in experiments using HANDS-kuchibue on-line handwritten character database. Results show that the method is effective in reducing candidates, improving accuracy, and saving computational costs.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) probability of correctness / on-line handwriting text recognition / bigram-based post-processing
Paper # TL2001-57
Date of Issue

Conference Information
Committee TL
Conference Date 2002/3/7(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 Thought and Language (TL)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Bigram-based Post-processing for On-line Handwriting Recognition Using Correctness Evaluation
Sub Title (in English)
Keyword(1) probability of correctness
Keyword(2) on-line handwriting text recognition
Keyword(3) bigram-based post-processing
1st Author's Name Hiromitsu KAWAJIRI
1st Author's Affiliation Hypermedia Research Center, SANYO Electric Co., Ltd.()
2nd Author's Name Akira NAKAMURA
2nd Author's Affiliation Hypermedia Research Center, SANYO Electric Co., Ltd.
Date 2002/3/7
Paper # TL2001-57
Volume (vol) vol.101
Number (no) 710
Page pp.pp.-
#Pages 8
Date of Issue