De-Emphasis of Distracting Image Regions Using Texture Power Maps
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-orde...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
2005
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/30220 |
| _version_ | 1811069543879016448 |
|---|---|
| author | Su, Sara L. Durand, Frédo Agrawala, Maneesh |
| author_facet | Su, Sara L. Durand, Frédo Agrawala, Maneesh |
| author_sort | Su, Sara L. |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T08:12:01Z |
| format | Article |
| id | mit-1721.1/30220 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T08:12:01Z |
| publishDate | 2005 |
| record_format | dspace |
| spelling | mit-1721.1/302202019-04-09T17:16:12Z De-Emphasis of Distracting Image Regions Using Texture Power Maps Su, Sara L. Durand, Frédo Agrawala, Maneesh Image processing computational photography saliency visual attention power map 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. Singapore-MIT Alliance (SMA) 2005-12-14T19:02:18Z 2005-12-14T19:02:18Z 2006-01 Article http://hdl.handle.net/1721.1/30220 en Computer Science (CS) 9465431 bytes application/pdf application/pdf |
| spellingShingle | Image processing computational photography saliency visual attention power map Su, Sara L. Durand, Frédo Agrawala, Maneesh De-Emphasis of Distracting Image Regions Using Texture Power Maps |
| title | De-Emphasis of Distracting Image Regions Using Texture Power Maps |
| title_full | De-Emphasis of Distracting Image Regions Using Texture Power Maps |
| title_fullStr | De-Emphasis of Distracting Image Regions Using Texture Power Maps |
| title_full_unstemmed | De-Emphasis of Distracting Image Regions Using Texture Power Maps |
| title_short | De-Emphasis of Distracting Image Regions Using Texture Power Maps |
| title_sort | de emphasis of distracting image regions using texture power maps |
| topic | Image processing computational photography saliency visual attention power map |
| url | http://hdl.handle.net/1721.1/30220 |
| work_keys_str_mv | AT susaral deemphasisofdistractingimageregionsusingtexturepowermaps AT durandfredo deemphasisofdistractingimageregionsusingtexturepowermaps AT agrawalamaneesh deemphasisofdistractingimageregionsusingtexturepowermaps |