Presentation 2006-02-24
Proposal and Experiment of Feature Integration Method for Low-resolution Character Recognition
Makoto Nomura, Kazuhiko Yamamoto, Hirotaka Ohata, Kunihito Kato,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a new feature extraction method "Feature Integration Method" from low-resolution image sequence. This method extracts a feature directly from low-resolution images without reconstructing a high-resolution image. When the feature is extracted from low-resolution images, reconstruct a high-resolution image to get higher accuracy recognition result. To reconstruct a high-resolution image first is a general idea, and it is extracted the feature from that high-resolution image. On the other hand, our proposed method has different process of the feature extraction. Our proposed method extracts features from low-resolution images directly. Then the feature is constructed from these extracted features. This constructed feature has the advantage than the feature of the general idea. We show this advantage by character recognition experiments both database images and video images in this paper.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Character recognition / Low resolution / Feature extraction / Feature integration method / Four directional feature fields
Paper # TL2005-76,PRMU2005-211
Date of Issue

Conference Information
Committee PRMU
Conference Date 2006/2/17(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) Proposal and Experiment of Feature Integration Method for Low-resolution Character Recognition
Sub Title (in English)
Keyword(1) Character recognition
Keyword(2) Low resolution
Keyword(3) Feature extraction
Keyword(4) Feature integration method
Keyword(5) Four directional feature fields
1st Author's Name Makoto Nomura
1st Author's Affiliation Faculty of Engineering, Gifu University()
2nd Author's Name Kazuhiko Yamamoto
2nd Author's Affiliation Faculty of Engineering, Gifu University
3rd Author's Name Hirotaka Ohata
3rd Author's Affiliation Faculty of Engineering, Gifu University
4th Author's Name Kunihito Kato
4th Author's Affiliation Faculty of Engineering, Gifu University
Date 2006-02-24
Paper # TL2005-76,PRMU2005-211
Volume (vol) vol.105
Number (no) 615
Page pp.pp.-
#Pages 6
Date of Issue