Fuzzy multipass filter for impulse noise removal in digital images

Authors:
Kenny Kal Vin Toh;Nor Ashidi Mat Isa
Affiliations:
Universiti Sains Malaysia, Imaging and Intelligent Systems Research Team, School of Electrical and Electronic Engineering, Penang, Malaysia;Universiti Sains Malaysia, Imaging and Intelligent Systems Research Team, School of Electrical and Electronic Engineering, Penang, Malaysia
Venue:
SITE'12 Proceedings of the 11th international conference on Telecommunications and Informatics, Proceedings of the 11th international conference on Signal Processing
Year:
2012

Citing 7
Cited 0

Adaptive fuzzy switching filter for images corrupted by impulse noise

Pattern Recognition Letters
Efficient impulse noise reduction via local directional gradients and fuzzy logic

Fuzzy Sets and Systems
A new impulse detection and filtering method for removal of wide range impulse noises

Pattern Recognition
Efficient removal of impulse noise from digital images

IEEE Transactions on Consumer Electronics
Noise adaptive soft-switching median filter

IEEE Transactions on Image Processing
A switching median filter with boundary discriminative noise detection for extremely corrupted images

IEEE Transactions on Image Processing
Using Uncorrupted Neighborhoods of the Pixels for Impulsive Noise Suppression With ANFIS

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a fuzzy multipass filter that effectively removes impulse noise in digital images. The proposed fuzzy inference mechanism is partly based on the well-known Fuzzy Inference Ruled by Else-action (FIRE) reasoning strategy, coupled with a newly introduced pseudo fuzzy rulebase that is represented by a set of simple logical operations. The FIRE mechanism is adopted to perform strong noise cancellation when impulses are detected, whereas the pseudo fuzzy rulebase conveniently simplifies the complicated computation and evaluation of a complex-structured rulebase in fuzzy filtering. Additionally, the proposed filter uses two inter-related fuzzy membership functions to increase its adaptiveness towards local noise statistics, which in turn has improved its restoration performance. Simulation results demonstrate the effectiveness and feasibility of the proposed fuzzy multipass filter.