Presentation 1998/12/11
Design of Data-Dependent Weighted Mean Filters Using Counter Propagation Networks
Mitsuji MUNEYASU, Yuuichi MIYAKE, Takao HINAMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a design method for data-dependent weighted mean filters by using counter propagation networks. The proposed filter consists of a weight controller and a weighted mean filter. This controller based on counter propagtion networks classifies an input vector into some cluster according to its pattern and selects the weights of the filter corresponding to its cluster. The proposed filter can reduce white Gaussian noise, effectively and has the edge-preserving property. A simulation example is given to illustrate the utility of the proposed technique.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) noise reduction / neural network / nonlinear filter / weighted mean filter / white Gaussian noise
Paper # DSP98-141
Date of Issue

Conference Information
Committee DSP
Conference Date 1998/12/11(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 Digital Signal Processing (DSP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Design of Data-Dependent Weighted Mean Filters Using Counter Propagation Networks
Sub Title (in English)
Keyword(1) noise reduction
Keyword(2) neural network
Keyword(3) nonlinear filter
Keyword(4) weighted mean filter
Keyword(5) white Gaussian noise
1st Author's Name Mitsuji MUNEYASU
1st Author's Affiliation Faculty of Engineering, Hiroshima University()
2nd Author's Name Yuuichi MIYAKE
2nd Author's Affiliation Faculty of Engineering, Hiroshima University
3rd Author's Name Takao HINAMOTO
3rd Author's Affiliation Faculty of Engineering, Hiroshima University
Date 1998/12/11
Paper # DSP98-141
Volume (vol) vol.98
Number (no) 451
Page pp.pp.-
#Pages 8
Date of Issue