De-Emphasis of Distracting Image Regions Using Texture Power Maps

DE-EMPHASIS OF DISTRACTING IMAGE REGIONS USING TEXTURE POWER MAPS

Sara L. Su^1,2, Frédo Durand¹, Maneesh Agrawala²
¹MIT CSAIL, ²Microsoft Research

Proceedings of Texture 2005, at ICCV 2005

ABSTRACT

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.

ARTICLES

De-Emphasis of Distracting Image Regions Using Texture Power Maps
Sara L. Su, Frédo Durand, and Maneesh Agrawala
4th IEEE International Workshop on Texture Analysis and Synthesis,
in conjunction with ICCV'05, pp. 119-124,
Beijing, China, October 2005
[paper] [bib]
De-Emphasis of Distracting Image Regions Using Texture Power Maps
Sara L. Su, Frédo Durand, and Maneesh Agrawala
2nd ACM SIGGRAPH Symposium on Applied Perception in Graphics and Visualization
(APGV'05), p. 164, A Coruña, Spain, August 2005
[abstract] [poster]
Image Editing with Texture Power Maps
Sara L. Su, Frédo Durand, and Maneesh Agrawala
Symposium on Computational Photography and Video (SCPV'05),
Cambridge, MA, May 2005
[abstract] [poster]
Perceptual Picture Emphasis Using Texture Power Maps
Sara L. Su
Master's thesis, Massachusetts Institute of Technology,
Cambridge, MA, January 2005
An Inverted Saliency Model for Display Enhancement
Sara L. Su, Frédo Durand, and Maneesh Agrawala
MIT Student Oxygen Workshop,
Ashland, MA, September 2004
[paper]

ACKNOWLEDGMENTS

We thank the MIT Graphics Group and anonymous reviewers for feedback; Paul Green and Eric Chan for invaluable assistance with data acquisition and analysis; and Aude Oliva, Ruth Rosenholtz, and their students for use of their eyetracker. This work was supported by NSF under Grant No. 0429739 and the Graduate Research Fellowship Program, MIT Project Oxygen, and the Royal Dutch/Shell Group.