Retagging Social Images Based on Visual and Semantic

The tags on social media websites such as Flickr are fre-quently imprecise and incomplete, thus there is still a gap between these tags and the actual content of the images. This paper proposes a social image “retagging ” scheme that aims at assigning images with better content descriptors. The refining process is formulated as an optimization frame-work based on the consistency between “visual similarity” and “semantic similarity ” in social images. An effective iter-ative bound optimization algorithm is applied to learn the optimal tag assignment. In addition, as many tags are in-trinsically not closely-related to the visual content of the images, we employ a knowledge-based method to differenti-ate visual content related from unrelated tags and then con-strain the tagging vocabulary of our automatic algorithm within the content related tags. Experimental results on a Flickr image collection demonstrate the effectiveness of this approach