Graph-spectral filter for removing mixture of gaussian and random impulsive noise

Yu Qiu, Zenggang Pu, Kiichi Urahama

Research output: Contribution to journalArticle

Abstract

We propose, in this lettei; a new type of image denois ing filter using a data analysis technique. We deal with pixels as data and extract the most dominant cluster from pixels in the filtering window. We output the centroid of the extracted cluster. We demonstrate that this graph- spectral filter can effectively reduce a mixture of Gaussian and random im pulsive noise.

Original languageEnglish
Pages (from-to)457-460
Number of pages4
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE94-A
Issue number1
DOIs
Publication statusPublished - Jan 1 2011

Fingerprint

Impulsive Noise
Impulse noise
Pixel
Pixels
Filter
Graph in graph theory
Centroid
Data analysis
Filtering
Output
Demonstrate

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

Graph-spectral filter for removing mixture of gaussian and random impulsive noise. / Qiu, Yu; Pu, Zenggang; Urahama, Kiichi.

In: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E94-A, No. 1, 01.01.2011, p. 457-460.

Research output: Contribution to journalArticle

@article{4e999c4c9d6041e4976f07e354a57771,
title = "Graph-spectral filter for removing mixture of gaussian and random impulsive noise",
abstract = "We propose, in this lettei; a new type of image denois ing filter using a data analysis technique. We deal with pixels as data and extract the most dominant cluster from pixels in the filtering window. We output the centroid of the extracted cluster. We demonstrate that this graph- spectral filter can effectively reduce a mixture of Gaussian and random im pulsive noise.",
author = "Yu Qiu and Zenggang Pu and Kiichi Urahama",
year = "2011",
month = "1",
day = "1",
doi = "10.1587/transfun.E94.A.457",
language = "English",
volume = "E94-A",
pages = "457--460",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "1",

}

TY - JOUR

T1 - Graph-spectral filter for removing mixture of gaussian and random impulsive noise

AU - Qiu, Yu

AU - Pu, Zenggang

AU - Urahama, Kiichi

PY - 2011/1/1

Y1 - 2011/1/1

N2 - We propose, in this lettei; a new type of image denois ing filter using a data analysis technique. We deal with pixels as data and extract the most dominant cluster from pixels in the filtering window. We output the centroid of the extracted cluster. We demonstrate that this graph- spectral filter can effectively reduce a mixture of Gaussian and random im pulsive noise.

AB - We propose, in this lettei; a new type of image denois ing filter using a data analysis technique. We deal with pixels as data and extract the most dominant cluster from pixels in the filtering window. We output the centroid of the extracted cluster. We demonstrate that this graph- spectral filter can effectively reduce a mixture of Gaussian and random im pulsive noise.

UR - http://www.scopus.com/inward/record.url?scp=78650929234&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650929234&partnerID=8YFLogxK

U2 - 10.1587/transfun.E94.A.457

DO - 10.1587/transfun.E94.A.457

M3 - Article

VL - E94-A

SP - 457

EP - 460

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 1

ER -