[1]ZHAO Chun-hui,XIAO Xiao-jun.Optimizing stacked filters with mirrored threshold decomposition using an improved clone selection and PSO algorithm[J].CAAI Transactions on Intelligent Systems,2008,3(2):129-134.
Copy
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
3
Number of periods:
2008 2
Page number:
129-134
Column:
学术论文—智能系统
Public date:
2008-04-25
- Title:
-
Optimizing stacked filters with mirrored threshold decomposition using an improved clone selection and PSO algorithm
- Author(s):
-
ZHAO Chun-hui; XIAO Xiao-jun
-
College of Information and Communication Engineering, Harbin Engineering Univer sity, Harbin 150001,China
-
- Keywords:
-
mirrored threshold decomposition; positive Boolean function (PBF); stacked filters; clone selection algorithm; Particle swarm optimization(PSO)
- CLC:
-
TN911.26
- DOI:
-
-
- Abstract:
-
Stack filters are a class of nonlinear digital filters with sliding windows. Their two main properties are threshold decomposition and stacking. Optimal design of these filters requires optimization of a positive Boolean function (PBF). Optimization of stacked filters using traditional algorithms is easily trapped in a local optimum. To prevent this in recent years the bionic clone selection and PSO algorithms were proposed. The combination of these two algorithms avoids the problem of falling into a local minimum, greatly improving convergence speed and accuracy.Experimental results show that optimally stacked filters effectively suppress noise while retaining details of images and enhancing filtering capability.