Title
Robust algorithm for broad impulse noise removal utilizing intensity distance and intensity height methodologies.
Abstract
In this manuscript, a new algorithm to reduce impulse noise from digital images has been proposed. This algorithm is based on switching median filtering approach, and therefore, it can be generally divided into two main stages; impulse noise detection stage and impulse noise cancellation stage. Modifications towards a well-known boundary discriminative noise detection method have been made. First, rather than using any sorting algorithm, we determine the local median values from manipulated local histograms. This solution makes the execution of the algorithm faster. Next, in the noise detection stage, in addition to the originally proposed intensity distance differential approach, the new method includes intensity height differential approach to reduce false detection rate. Then, instead of using adaptive approach in noise cancellation stage, our approach uses iterative approach, which has better local content preservation ability. Broad impulse noise model has been employed in this experiment. Based on the evaluations from root mean square error, false positive detection rate, false negative detection rate, mean structure similarity index, processing time, and visual inspection, it is shown that the proposed method is the best method when compared with seven other state-of-the-art median filtering techniques.
Year
DOI
Venue
2014
10.1007/s11760-013-0538-y
Signal, Image and Video Processing
Keywords
Field
DocType
Digital image processing, Impulse noise, Salt-and-pepper noise, Switching median filter, Impulse noise detection, Impulse noise cancellation
Value noise,Median filter,Noise measurement,Noise (signal processing),Pattern recognition,Algorithm,Salt-and-pepper noise,Artificial intelligence,Impulse noise,Gaussian noise,Mathematics,Gradient noise
Journal
Volume
Issue
ISSN
8
2
1863-1711
Citations 
PageRank 
References 
1
0.35
8
Authors
2
Name
Order
Citations
PageRank
Sin Hoong Teoh110.35
Haidi Ibrahim21158.83