Impulse Noise Removal by use of Median M-Type KNN Filter

V. Ponomaryov, F. Gallegos-Funes, and L. Nino-de-Rivera (Mexico)

Keywords

 robust estimators, MM-KNN filter.

Abstract

The ability of the median M-type K-nearest neighbor (MM-KNN) filter to remove impulse noise from corrupted images is investigated. This filter uses R and M estimators combined with different influence functions. Simulation results have shown that the restoration performance (preservation of small-scale details and impulse noise suppression) is better in comparison with another known filters.

Important Links:

• DOI:
• From Proceeding (370) Signal Processing, Pattern Recognition, and Applications - 2002

Go Back