Rough sets for Eliciting Symptoms for Landuse Class Conflict

Conflicts are one of the most characteristic attributes in remote sensing multilayer imagery. Many models for conflict resolution and analysis have been proposed and studied till time. Class conflict occurs when there is presence of spectrally indiscernible distinct classes and how the human experts understand it based on his/her expertise. In this paper we try to outline a new approach to conflict analysis using rough set theory. The paper deals with the idea of eliminating the spectral band causing the conflict between opinions of two experts. It also highlights how the training data set can be used for this class conflicts analysis