Title :
Design of weighted order statistic filters using the perceptron algorithm
Author :
Jeong, Byeongjang ; Lee, Yong Hoon
Author_Institution :
Dept. of Electr. Eng., Korea Adv. Inst. of Sci. & Technol., Taejon, South Korea
fDate :
11/1/1994 12:00:00 AM
Abstract :
We observe that the design of optimal weighted order statistic (WOS) filters under the mean absolute error criterion can be thought of as a two-class linear classification problem. Based on this observation, the perceptron algorithm is applied to designing WOS filters. It is shown experimentally that the perceptron algorithm can find optimal or near-optimal WOS filters in practical situations
Keywords :
digital filters; filtering theory; image enhancement; linear network synthesis; neural nets; perceptrons; design; image enhancement; mean absolute error criterion; perceptron algorithm; two-class linear classification problem; weighted order statistic filters; Algorithm design and analysis; Circuits; Digital filters; Error analysis; Finite wordlength effects; Linear matrix inequalities; Linear systems; Nonlinear filters; Signal processing algorithms; Statistics;
Journal_Title :
Signal Processing, IEEE Transactions on
