Interactive relevance feedback mechanism for image retrieval using rough set

Recently, how to express human perception has become one of the most active research topics in image retrieval. In this paper, we propose a relevance feedback mechanism that can express objectively human perception by using rough set theory in retrieval system. The mechanism makes full use of the inherent advantages of rough set to solve the difficulty that the retrieval system cannot express human perception. In the end, an image retrieval system – “Basestar”, which is based on the technology, is introduced to illustrate the retrieval performance.