A neural network implementation of the median filter

TitleA neural network implementation of the median filter
Publication TypeConference Paper
Year of Publication1989
AuthorsShi, P., and R. K. Ward
Conference NameCommunications, Computers and Signal Processing, 1989. Conference Proceeding., IEEE Pacific Rim Conference on
Pagination513 -516
Date Publishedjun.
Keywordsfiltering and prediction theory, image enhancement, median filter, neural nets, neurons, nonnegative integers, parallel neural network, picture processing, real-time enhancement, time delay, video pictures

A parallel neural network for finding the median of an array of nonnegative integers is proposed. The processing time of the network is equal to the time delay of five neurons. This is constant irrespective of the number of elements in the array. This is in contrast with the conventional serial and parallel implementations where the delay time increases as the array gets larger. The proposed network makes the real-time enhancement of images and video pictures possible


a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2021 The University of British Columbia