Nonlinear Digital FiltersThe function of a filter is to transform a signal into another one more suit able for a given purpose. As such, filters find applications in telecommunica tions, radar, sonar, remote sensing, geophysical signal processing, image pro cessing, and computer vision. Numerous authors have considered deterministic and statistical approaches for the study of passive, active, digital, multidimen sional, and adaptive filters. Most of the filters considered were linear although the theory of nonlinear filters is developing rapidly, as it is evident by the numerous research papers and a few specialized monographs now available. Our research interests in this area created opportunity for cooperation and co authored publications during the past few years in many nonlinear filter families described in this book. As a result of this cooperation and a visit from John Pitas on a research leave at the University of Toronto in September 1988, the idea for this book was first conceived. The difficulty in writing such a mono graph was that the area seemed fragmented and no general theory was available to encompass the many different kinds of filters presented in the literature. However, the similarities of some families of nonlinear filters and the need for such a monograph providing a broad overview of the whole area made the pro ject worthwhile. The result is the book now in your hands, typeset at the Department of Electrical Engineering of the University of Toronto during the summer of 1989. |
Contents
Introduction | 1 |
Homomorphic filters | 5 |
Statistical preliminaries | 11 |
Image formation | 37 |
Median filters | 63 |
Digital filters based on order statistics | 117 |
Morphological image and signal processing | 151 |
Other editions - View all
Nonlinear Digital Filters: Principles and Applications Ioannis Pitas,Anastasios N. Venetsanopoulos No preview available - 2010 |
Common terms and phrases
adaptive additive algorithm analysis applications asymptotic binary calculation called chapter chosen close coefficients constant corresponding decomposition defined definition denotes depends described digital image distribution edge efficiency element equal estimator example exists function Gaussian given homomorphic IEEE Transactions image processing implementation important impulses impulsive noise input length light linear mathematical matrix mean median filter morphological moving average filter noise nonlinear filters object observations obtained opening operations order statistics Original outliers output performance pixels positive presented preservation probability problem Proc properties proven quadratic random recursive regions relation removal respectively robust robust estimation root samples scale seen sequence shown in Figure Signal Processing skeleton Speech and Signal square standard deviation step structure tends term theory threshold tion Transactions on Acoustics transformation two-dimensional values variables variance vision Volterra window