Weighted fuzzy mean filters for heavy-tailed noise removal

Chang Shing Lee, Yau Hwang Kuo, Pao Ta Yu

Research output: Contribution to conferencePaper

16 Citations (Scopus)

Abstract

A new fuzzy filter, called Weighted Fuzzy Mean (WFM) filter is proposed and analyzed in this paper. The WFM filter is powerful for removing heavy additive impulse noises from images. By the filtering of each WFM filter, the filtered output signal is the mean value of the corrupted signals in a sample matrix, and these signals are weighted respectively by a membership grade of an associated fuzzy number stored in a knowledge base. The knowledge base contains a set of fuzzy numbers decided by experts or derived from the histogram of referred image. When the probability of occurrence of mixed impulse noises is over 0.3, the WFM filter can recover the noise-corrupted image quite well in contrast with the conventional filters, for examples, the median filters, nonlinear mean filters, RCRS, WOS, CWM, and stack filters, based on the Mean Absolute Error (MAE) and Mean Square Error (MSE) criteria. Besides, on the subjective evaluation of filtered images, the WFM filter results in a higher quality of global restoration.

Original languageEnglish
Pages601-606
Number of pages6
Publication statusPublished - 1995 Dec 1
EventProceedings of the 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society, (ISUMA - NAFIPS'95) - College Park, MD, USA
Duration: 1995 Sep 171995 Sep 20

Other

OtherProceedings of the 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society, (ISUMA - NAFIPS'95)
CityCollege Park, MD, USA
Period95-09-1795-09-20

Fingerprint

Noise Removal
Impulse noise
Fuzzy filters
Filter
Median filters
Mean square error
Restoration
Impulse Noise
Fuzzy numbers
Knowledge Base
Fuzzy Filter
Median Filter
Subjective Evaluation
Mean Value
Histogram
Filtering
Output

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Mathematics(all)

Cite this

Lee, C. S., Kuo, Y. H., & Yu, P. T. (1995). Weighted fuzzy mean filters for heavy-tailed noise removal. 601-606. Paper presented at Proceedings of the 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society, (ISUMA - NAFIPS'95), College Park, MD, USA, .
Lee, Chang Shing ; Kuo, Yau Hwang ; Yu, Pao Ta. / Weighted fuzzy mean filters for heavy-tailed noise removal. Paper presented at Proceedings of the 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society, (ISUMA - NAFIPS'95), College Park, MD, USA, .6 p.
@conference{bf347bc5ddc2471993d3d26cb907621a,
title = "Weighted fuzzy mean filters for heavy-tailed noise removal",
abstract = "A new fuzzy filter, called Weighted Fuzzy Mean (WFM) filter is proposed and analyzed in this paper. The WFM filter is powerful for removing heavy additive impulse noises from images. By the filtering of each WFM filter, the filtered output signal is the mean value of the corrupted signals in a sample matrix, and these signals are weighted respectively by a membership grade of an associated fuzzy number stored in a knowledge base. The knowledge base contains a set of fuzzy numbers decided by experts or derived from the histogram of referred image. When the probability of occurrence of mixed impulse noises is over 0.3, the WFM filter can recover the noise-corrupted image quite well in contrast with the conventional filters, for examples, the median filters, nonlinear mean filters, RCRS, WOS, CWM, and stack filters, based on the Mean Absolute Error (MAE) and Mean Square Error (MSE) criteria. Besides, on the subjective evaluation of filtered images, the WFM filter results in a higher quality of global restoration.",
author = "Lee, {Chang Shing} and Kuo, {Yau Hwang} and Yu, {Pao Ta}",
year = "1995",
month = "12",
day = "1",
language = "English",
pages = "601--606",
note = "Proceedings of the 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society, (ISUMA - NAFIPS'95) ; Conference date: 17-09-1995 Through 20-09-1995",

}

Lee, CS, Kuo, YH & Yu, PT 1995, 'Weighted fuzzy mean filters for heavy-tailed noise removal', Paper presented at Proceedings of the 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society, (ISUMA - NAFIPS'95), College Park, MD, USA, 95-09-17 - 95-09-20 pp. 601-606.

Weighted fuzzy mean filters for heavy-tailed noise removal. / Lee, Chang Shing; Kuo, Yau Hwang; Yu, Pao Ta.

1995. 601-606 Paper presented at Proceedings of the 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society, (ISUMA - NAFIPS'95), College Park, MD, USA, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Weighted fuzzy mean filters for heavy-tailed noise removal

AU - Lee, Chang Shing

AU - Kuo, Yau Hwang

AU - Yu, Pao Ta

PY - 1995/12/1

Y1 - 1995/12/1

N2 - A new fuzzy filter, called Weighted Fuzzy Mean (WFM) filter is proposed and analyzed in this paper. The WFM filter is powerful for removing heavy additive impulse noises from images. By the filtering of each WFM filter, the filtered output signal is the mean value of the corrupted signals in a sample matrix, and these signals are weighted respectively by a membership grade of an associated fuzzy number stored in a knowledge base. The knowledge base contains a set of fuzzy numbers decided by experts or derived from the histogram of referred image. When the probability of occurrence of mixed impulse noises is over 0.3, the WFM filter can recover the noise-corrupted image quite well in contrast with the conventional filters, for examples, the median filters, nonlinear mean filters, RCRS, WOS, CWM, and stack filters, based on the Mean Absolute Error (MAE) and Mean Square Error (MSE) criteria. Besides, on the subjective evaluation of filtered images, the WFM filter results in a higher quality of global restoration.

AB - A new fuzzy filter, called Weighted Fuzzy Mean (WFM) filter is proposed and analyzed in this paper. The WFM filter is powerful for removing heavy additive impulse noises from images. By the filtering of each WFM filter, the filtered output signal is the mean value of the corrupted signals in a sample matrix, and these signals are weighted respectively by a membership grade of an associated fuzzy number stored in a knowledge base. The knowledge base contains a set of fuzzy numbers decided by experts or derived from the histogram of referred image. When the probability of occurrence of mixed impulse noises is over 0.3, the WFM filter can recover the noise-corrupted image quite well in contrast with the conventional filters, for examples, the median filters, nonlinear mean filters, RCRS, WOS, CWM, and stack filters, based on the Mean Absolute Error (MAE) and Mean Square Error (MSE) criteria. Besides, on the subjective evaluation of filtered images, the WFM filter results in a higher quality of global restoration.

UR - http://www.scopus.com/inward/record.url?scp=38449106703&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38449106703&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:38449106703

SP - 601

EP - 606

ER -

Lee CS, Kuo YH, Yu PT. Weighted fuzzy mean filters for heavy-tailed noise removal. 1995. Paper presented at Proceedings of the 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society, (ISUMA - NAFIPS'95), College Park, MD, USA, .