Abstract
A high performance detection (HPD) filter is proposed for impulse noise removal in images. In this approach, the noisy pixels are detected iteratively through several phases, based on a set of unique similarity criteria. Simulation results show that the HPD filter outperforms others at medium to high noise rates and suppresses impulse noise effectively while preserving image details, even thin lines.
Original language | English |
---|---|
Pages (from-to) | 192-194 |
Number of pages | 3 |
Journal | Electronics Letters |
Volume | 44 |
Issue number | 3 |
DOIs | |
State | Published - 2008 |