Multimedia retrieval in social networks for photo book creation

Abstract

Social networks such as Facebook witness an explosively growing number of shared photos. People enjoy taking photos of each other in public and private events, upload them, tag each other and continue commenting on each other's photos. These photos are considered to be great assets for many users who would like to create photo books from them, so that they can show their experience and special events to friends and family. However, finding the required photos is not an easy task, because they can be distributed over different friends and albums with different tags and annotations, and they can be of different importance to the user. In this paper we propose a software prototype which employs multimedia retrieval methods to allow an easy creation of photo books from social networks. In our system photos are first clustered to events which can potentially be distributed over the social network, and then selected based on their importance and finally distributed and laid out over the pages of a photo book. The functionalities of our system are implemented and deployed as web services and our presentation layer is a wizard-like Facebook application.