Boost search relevance for tag-based social image retrieval

Social media sharing Web sites like Flickr allow users to annotate images with free tags, which greatly facilitate social image search and browsing. However, currently tag-based image search on Flickr does not provide the option of relevance-based ranking, i.e., the search results cannot be ranked according to their relevance levels with respect to the query tag, and this has limited the effectiveness of tagbased search. In this paper, we propose a relevance-based ranking scheme for social image search, aiming to automatically rank images according to their relevance to the query tag. It integrates both the visual consistency between images and the semantic correlation between tags in a unified optimization framework. We propose an iterative method to solve the optimization problem, and the relevance-based ranking can thus be accomplished. Experimental results on real Flickr image collection demonstrate the effectiveness of the proposed approach.

1. INTRODUCTION

There is an explosion of community-contributed multimedia content available online, such as Youtube, Flickr, Zooomr, etc. Rather than simply searching for and passively consuming information, such media repositories promote users to collaboratively create, evaluate and distribute media information, which underscores a transformation of the Web as fundamental as its birth [1]. Flickr [2], which is the earliest and most popular photo sharing website, claims to host over 200-million personal photos¹

Flickr Blog, Jan. 2008. http://flickr.com/blog.

annotated with descriptive keywords called tags. With the rich tags as metadata, users can freely organize, index and search the shared media content, which provides opportunities to make large-scale media retrieval work in practice.