Presentation 2010-03-05
Improvement of Gaussian noise removal by using enhanced total variation filter
Sho MIURA, Tomoyuki HIRANO, Hiroyuki TSUJI, Tomoaki KIMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) TV filter is a nonlinear filter that can remove Gaussian noise effectively, based on variational principle. It traditionally uses a single λ determined by noise estimation for each image. In this paper, we proposed an enhanced TV filter that takes a different λ for each pixel, depending on the local window surrounding the center pixel. Experimental results show that the enhanced TV filter mostly restores an input image better than the other traditional filters according to the PSNR values.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) TV filter / nonlinear filter / image restoration / Gaussian noise removal
Paper # SIS2009-67
Date of Issue

Conference Information
Committee SIS
Conference Date 2010/2/25(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 Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Improvement of Gaussian noise removal by using enhanced total variation filter
Sub Title (in English)
Keyword(1) TV filter
Keyword(2) nonlinear filter
Keyword(3) image restoration
Keyword(4) Gaussian noise removal
1st Author's Name Sho MIURA
1st Author's Affiliation Graduate School of Kanagawa Institute of technology()
2nd Author's Name Tomoyuki HIRANO
2nd Author's Affiliation Graduate School of Kanagawa Institute of technology
3rd Author's Name Hiroyuki TSUJI
3rd Author's Affiliation Graduate School of Kanagawa Institute of technology
4th Author's Name Tomoaki KIMURA
4th Author's Affiliation Graduate School of Kanagawa Institute of technology
Date 2010-03-05
Paper # SIS2009-67
Volume (vol) vol.109
Number (no) 447
Page pp.pp.-
#Pages 6
Date of Issue