Modeling Data and User Characteristics by Peer Indexing in Content-based Image Retrieval

Modeling the characteristics of specific images and individual users is a critical issue in content-based image retrieval but insufficiently addressed by the current retrieval approaches. In this paper, we propose a novel approach to dataadaptive and user-adaptive image retrieval based on the idea of peer indexing—describing an image through semantically relevant peer images. Specifically, we associate each image with two-level peer index that models the “data characteristics” of the image as well as the “user characteristics” of individual users with respect to this image. Based on two-level image peer indices, retrieval parameters including query vectors and similarity metric can be optimized towards both data and user characteristics by applying the pseudo feedback strategy. A cooperative framework is proposed under which peer indices and image visual features are integrated to facilitate dataand useradaptive image retrieval. Extensive experiments have been conducted on real-world images to verify the effectiveness of our approach.