Reliable tags using image similarity
Lyndon S. Kennedy, Malcolm Slaney, Kilian Q. Weinberger · 2009
This paper describes an approach for finding image descriptors or tags that are highly reliable and specific. Reliable, in this work, means that the tags are related to the image's visual content, which we verify by finding two or more real people who agree that the tag is applicable. Our work differs from prior work by mining the photographer's (or web master's) original words and seeking inter-subject agreement for images that we judge to be highly similar. By using the photographer's words we gain specificity since the photographer knows that the image represents something specific, such as the Augsburg Cathedral; whereas random people from the web playing a labeling game might not have this knowledge. We describe our approach and demonstrate that we identify reliable tags with greater specificity than human annotators.