Noise detection-based median filters have been widely adopted to reduce impulse noise in images. However

more pixels were misclassified at the high noise density. The drawback has negative effect on image filtering. In order to overcome the drawback

in this paper

the upper-lower median-type noise detector is proposed. Based on the noise detector

an adaptive median algorithm is presented. Experimental results show that the new algorithm can effectively remove the impulse noise and preserve more details of original images.