Abstract:- Social media sharingwebsites like Flickr allow users to annotate images with free tags, whichsignificantly contribute to the development of the web image re-trivial andorganization. Tag-based image searchis an important method to find images contributed by social users in suchsocial websites. However, how to makethe top ranked result relevant and with diversity is challenging. In thispaper, we propose a social re-ranking system for tag-based image retrieval withthe consideration of images relevance and diversity.We aim at re-ranking imagesaccording to their visual information, semantic information and social clues.The initial results include images contributed by different social users.Usually each user contributes several images. First we sort these images byinter-user re-ranking. Users that have higher contribution to the given query rank higher. Then we sequentially implement intra-user re-ranking on the ranked users image set,and only the most relevant image from each user’s image set is selected.
Keywords: Database, Application mining, Image databases, Social and behavioralsciences, Economics, Psychology, Information Search and Retrieval Clustering