Presentation 2000/2/22
On the Character Pattern Extraction Applicable to Various Types of Images : -A survey, and an example of the method-
Hideaki GOTO, Hirotomo ASO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) With the recent expanding application of the OCR, computers have to extract character patterns not only from the scanned document images but also from the various types of images including scene images. In this report, we first discuss the needs of developing the methods which can handle various types of images. We present a survey of character pattern extraction methods which have been designed separately according to the image type, and introduce some difficulties we must overcome. Finally, a unified character pattern extraction method is proposed. The method is based on the local multilevel thresholding and the region growing. It can extract small character patterns form scanned document images, and is also applicable to the scene images.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) character pattern extraction / scene image / document image / complex background / local multilevel thresholding
Paper # PRMU99-234
Date of Issue

Conference Information
Committee PRMU
Conference Date 2000/2/22(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Vice Chair

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) On the Character Pattern Extraction Applicable to Various Types of Images : -A survey, and an example of the method-
Sub Title (in English)
Keyword(1) character pattern extraction
Keyword(2) scene image
Keyword(3) document image
Keyword(4) complex background
Keyword(5) local multilevel thresholding
1st Author's Name Hideaki GOTO
1st Author's Affiliation Education Center for Information Processing, Tohoku University()
2nd Author's Name Hirotomo ASO
2nd Author's Affiliation Graduate School of Engineering, Tohoku University
Date 2000/2/22
Paper # PRMU99-234
Volume (vol) vol.99
Number (no) 649
Page pp.pp.-
#Pages 8
Date of Issue