Results selection diversity for web image retrieval

We describe a re-ranking method called dual rank to improve web image retrieval by clustering and reordering the images retrieved from an image search engine. General image retrieval exploits text and links the structure or little visual information to 'understand' the content of the web images, and usually lack the discriminative power to deliver visually diverse search results. The framework of dual rank is composed of inter-cluster rank and intra-cluster rank. To address the clustering problem, we first utilize a multipartite graph model to represent images and features, then formulate clustering as a constrained multi-objective optimization problem, which can be efficiently solved by semi-definite programming. We employ inter-cluster ranking function and intra-cluster ranking function to rank clusters and images, respectively. A representative image is selected from each cluster which together forms a diverse result set and as the optimal results for a query. We fuse different image features (text, colour, shape, texture, etc.) to improve the effect of clustering. Our method is evaluated against a standard search engine and significant improvements are reported in terms of Mean average precision, D@n and user experience.