Presentation 2004/5/20
Generative Learning Method for the Recognition of Low-Resolution Characters Using the Subspace Method
Hiroyuki ISHIDA, Shinsuke YANADUME, Yoshito MEKADA, Ichiro IDE, Hiroshi MURASE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We are developing a recognition system for low-resolution characters using the Subspace method. This method identifies target characters by comparing the similarity between the characters and each subspace, which approximates the patterns of a character. Learning degraded characters is necessary for the recognition by the Subspace method. Former methods made use of characters captured by a camera, which requires us to collect characters of all categories in various conditions. In this report, we propose a new learning method, which generates the degraded characters for learning by a point spread function estimated beforehand by captured images. We confirmed the usefulness of our method by experiments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Character Recognition / Low Resolution / Subspace Method / Movie / Learning Method
Paper # PRMU2004-7,MI2004-7,WIT2004-7
Date of Issue

Conference Information
Committee WIT
Conference Date 2004/5/20(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 Well-being Information Technology(WIT)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Generative Learning Method for the Recognition of Low-Resolution Characters Using the Subspace Method
Sub Title (in English)
Keyword(1) Character Recognition
Keyword(2) Low Resolution
Keyword(3) Subspace Method
Keyword(4) Movie
Keyword(5) Learning Method
1st Author's Name Hiroyuki ISHIDA
1st Author's Affiliation Graduate School of Information Science, Nagoya University()
2nd Author's Name Shinsuke YANADUME
2nd Author's Affiliation Graduate School of Information Science, Nagoya University
3rd Author's Name Yoshito MEKADA
3rd Author's Affiliation School of Life System Science and Technology, Chukyo University
4th Author's Name Ichiro IDE
4th Author's Affiliation Graduate School of Information Science, Nagoya University
5th Author's Name Hiroshi MURASE
5th Author's Affiliation Graduate School of Information Science, Nagoya University
Date 2004/5/20
Paper # PRMU2004-7,MI2004-7,WIT2004-7
Volume (vol) vol.104
Number (no) 92
Page pp.pp.-
#Pages 6
Date of Issue