On the general design problem of 2-dimensional recursive filters by using neural networks
Nikolaos E. Mastorakis, Valeri Mladenov · TU/e Research Portal · 2002
Abstract:- In this paper, a new design method for two-dimensional (2-D) recursive digital filters using Neural Networks is proposed. The design of the 2-D filter is reduced to a constrained minimization problem the solution of which is achieved by the convergence of an appropriate Neural Network. Here, the method given in the previous authors work [29] has been substantially improved by introducing a better approximation function. Numerical example is given as well.