De-Emphasis of Distracting Image Regions Using Texture Power Maps
Author(s)
Su, Sara L.; Durand, Frédo; Agrawala, Maneesh
DownloadCS005.pdf (9.026Mb)
Metadata
Show full item recordAbstract
We present a post-processing technique that selectively reduces the salience of distracting regions in an image. Computational models of attention predict that texture variation influences bottom-up attention mechanisms. Our method reduces the spatial variation of texture using power maps, high-order features describing local frequency content in an image. Modification of power maps results in effective regional de-emphasis. We validate our results quantitatively via a human subject search experiment and qualitatively with eye tracking data.
Date issued
2006-01Series/Report no.
Computer Science (CS)
Keywords
Image processing, computational photography, saliency, visual attention, power map