A fusion filtering algorithm based on D-S theory of evidence is proposed to combat shortcomings of linear and nonlinear filtering techniques. Firstly it analy zeshow and to what degree D-S theory of evidence can result in limitations, and then takes measures to annul dependencies among evidences and adaptively assigns contradictory information to conflict-relevant pixels, thus improving the combination criteria of D-S theory of evidence as well as increasing its fusion capability. On this foundation, and for the disadvantage in hybrid filters of great risk of misjudging image edges, lower reliability, and bad error tolerance, we add a multiple sub-source adjudging criteria, and utilize modified combination criteria in D-S theory of evidence to perform fusion judgments. Subsequent experimental resuits show the validity of the algorithm, thus providing a new way to improve image filtering techniques.
展开▼