Presentation 2012/1/12
Aggregating Visual Confirmation Method for Character Recognition Result
Yasuaki Iwata, Mitsuharu Oba, Toshiko Matsumoto, Takashi Onoyama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose an aggregating visual confirmation method for character recognition result by OCR to reduce the cost of document scanning and capture. Our method has two features. First, it has a clustering algorithm which is based on the recognition result and on the shape feature of the string image. Second, it creates the composite image by superimposing the images which are classified in the same cluster. The composite image enables operators to determine whether it consists of the same string image. Therefore, the operators can confirm and correct the recognition results in the same clusters at a time by comparing them. The experiment show that our method could cut down the number of visual confirmation by 39%.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # Vol.2012-CVIM-180 No.4
Date of Issue

Conference Information
Committee CQ
Conference Date 2012/1/12(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 Communication Quality (CQ)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Aggregating Visual Confirmation Method for Character Recognition Result
Sub Title (in English)
Keyword(1)
1st Author's Name Yasuaki Iwata
1st Author's Affiliation Hitachi Solutions, Ltd.()
2nd Author's Name Mitsuharu Oba
2nd Author's Affiliation Hitachi Solutions, Ltd.
3rd Author's Name Toshiko Matsumoto
3rd Author's Affiliation Hitachi Solutions, Ltd.
4th Author's Name Takashi Onoyama
4th Author's Affiliation Hitachi Solutions, Ltd.
Date 2012/1/12
Paper # Vol.2012-CVIM-180 No.4
Volume (vol) vol.111
Number (no) 378
Page pp.pp.-
#Pages 6
Date of Issue