Adaptive image restoration using recursive image filters

Abstract

Examines adaptive image processing in a recursive filtering framework. Recursive filters offer the potential of a large implicit region of support with few calculations per pixel, but have been generally ignored in light of additional concerns of stability, causality, and phase. The use of simple adaptive recursive filters for image restoration is examined. Adaptive filter behavior is achieved by changing the position of poles of the filter depending on local image characteristics. Results show that issues of stability, causality, and phase can be addressed and that traditional nonrecursive adaptive image filters can be successfully emulated.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>