De-Emphasis of Distracting Image Regions Using Texture Power Maps
Sara L. Su, Frédo Durand, Maneesh Agrawala
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.
High frequencies have been made more uniform in this texture equalized image. False-color power maps show the change in high-frequency distribution.
Research Paper
De-Emphasis of Distracting Image Regions Using Texture Power Maps
Texture 2005: Proceedings of the 4th IEEE International Workshop on Texture Analysis and Synthesis in conjunction with ICCV'05, pp. 119-124, Beijing, China, October 2005