Decision Based Median Filter using Particle Swarm Optimization for Impulsive Noise
No Thumbnail Available
Date
2013
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Infrared image sensors and communication medium often introduce impulse noise in image
acquisition and transmission. Most commonly available filters to remove impulsive noises are median fillers
with different versions, but the most important drawbacks identified with them are low noise suppression and
edge blurring. To preserve the sharp and valuable information present in the image, the filtering algorithms
should preserve the information available in them. The proposed work consists o f particle swarm optimization
based weight adaptation approach in the design of the filter. The filter weights are adapted and optimized
directly to restore a corrupted pixel in a mean square sense. This proposed work results in replacement of noisy
pixels by near originals along with its edge direction. The objective parameters used are Peak Signal to Noise
Ratio, Mean Absolute Error, and Correlation. This proposed research work is designed at presenting a new
filtering framework for impulse noise removal using Particle Swarm Optimization.