Re-ranking algorithm using clustering and relevance feedback for image retrieval

In conventional content-based image retrieval (CBIR) systems, it is often observed that images visually dissimilar to a query image are ranked high in retrieval results, which affects the retrieval effectiveness. To remedy this problem, we re-rank the retrieved images via clustering and relevance feedback. Based on conventional CBIR system, the retrieved images are analyzed using clustering method, and the weights of each feature component are updated. Then, the rank of the results is adjusted according to the distance of a cluster from a query. Experimental results show that our re-ranking algorithm achieves a more rational ranking of retrieval results compared with existing methods.