Using eye-tracking to assess different image retargeting methods

Assessing media retargeting results is not a trivial issue. When resizing one image to a particular percentage of its original size, some content has to be removed, which may affect the image's original meaning and/or composition. We examine the impact of the retargeting process on human fixations, by gathering eye-tracking data for a representative benchmark of retargeted images. We compute their derived saliency maps as input to a set of computational image distance metrics. When analyzing the fixations, we found that even strong artifacts may go unnoticed for areas outside the original regions of interest. We also note that the most important alterations in semantics are due to content removal. Since using an eye tracker is not always a feasible option, we additionally show how an existing model of prediction of human fixations also works sufficiently well in a retargeting context.