Presentation 2002/1/3
Parameter Estimation to Remove Gaussian / Impulsive Noise Using a Kalman Filter
Keisuke YAMAMOTO, Masahiro IWAHASHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Kalman filtering approach, which is one of the methods to remove some additive noises, can be adaptive for statistical property of the image since it exploits the image modeling. To remove the noise, in general, the Kalman filtering requires a complex procedure to estimate parameters such as statistics of the original image and property of the observed noise. So far, a parameter estimation method was proposed, however, its performance of impulsive noise removal is not enough high because this method aims at removing the Gaussian noise. In this report, we propose a method to estimate parameters in order to remove both Gaussian noise and also impulsive noise by using nonlinear technique. Simulation results show that the proposed method improves performance of impulsive noise removal by approximately 30% in MSE (mean square error) compared to the conventional method keeping enough performance of Gaussian noise removal.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Kalman Filter / Noise Removal / Parameter Estimation / Nonlinear Technique
Paper # 2001-DSP-146,2001-SAT-104,2001-RCS-204
Date of Issue

Conference Information
Committee RCS
Conference Date 2002/1/3(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 Radio Communication Systems (RCS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Parameter Estimation to Remove Gaussian / Impulsive Noise Using a Kalman Filter
Sub Title (in English)
Keyword(1) Kalman Filter
Keyword(2) Noise Removal
Keyword(3) Parameter Estimation
Keyword(4) Nonlinear Technique
1st Author's Name Keisuke YAMAMOTO
1st Author's Affiliation Department of Electrical Engineering, Nagaoka University of technology()
2nd Author's Name Masahiro IWAHASHI
2nd Author's Affiliation Department of Electrical Engineering, Nagaoka University of technology
Date 2002/1/3
Paper # 2001-DSP-146,2001-SAT-104,2001-RCS-204
Volume (vol) vol.101
Number (no) 544
Page pp.pp.-
#Pages 8
Date of Issue