A Survey on Tag Based Image Search Using Various Aspects

Computer Engineering

Day by day the amount of mobile devices and web services are increasing rapidly and the success of many online social media websites, which allow users to create and share media information such as images and videos as well as describe the media content with tags. Social media sharing websites like “Flickr” allow users to annotate images or pictures with free tags, which significantly support to the development of the web image retrieval and organization. Tag-based image search is an important method to find images contributed by social users in such social websites. However, how to make the top-high ranked result relevant and with diversity is challenging. In this project, we propose a social re-ranking system for tag-based image retrieval with the consideration of image’s relevance and diversity. We focus at re-ranking images according to their visual and semantic information and social clues. The initial results include photos contributed by different social users. Usually each user contributes several images. First we sort out these images by inter-user re-ranking. Users that have higher contribution to the given query rank higher. Then we gradually implement intra-user re-ranking on the ranked user’s image set and only the most relevant image from each user’s image set is selected. These images compose the final retrieved results. We make an inverted index structure for the social image dataset to accelerate the searching process. Experimental results on “Flickr” dataset show that our social re-ranking method is effective and efficient.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.