Re-ranking of image search results returned by proprietary search engine is becoming key focus of research in recent years. This re-ranking is very effective to present results more relevant to user's intention of search. In this paper, image search result re-ranking is proposed. This proposed re-ranking is proved effective in terms of better precision. Proposed method makes use of keyword clusters for query expansion. Visual features are used for detecting duplicate images in proposed method. Removing duplicates leads to further improve in precision and recall in retrieval result