This shows you the differences between two versions of the page.
publications:localtexture99 [2010/06/09 15:48] 127.0.0.1 external edit |
publications:localtexture99 [2012/08/22 11:08] (current) rosenholtz |
||
---|---|---|---|
Line 1: | Line 1: | ||
+ | ====== General-purpose localization of textured image regions ====== | ||
+ | ==== R. Rosenholtz ==== | ||
+ | ---- | ||
+ | |||
+ | =====Abstract===== | ||
+ | |||
+ | In computer vision and image processing, we often perform different processing on “objects” than on “texture.” In order to | ||
+ | do this, we must have a way of localizing textured regions of an image. For this purpose, we suggest a working definition of | ||
+ | texture: Texture is a substance that is more compactly represented by its statistics than by specifying the configuration of its | ||
+ | parts. Texture, by this definition, is stuff that seems to belong to the local statistics. Outliers, on the other hand, seem to | ||
+ | deviate from the local statistics, and tend to draw our attention, or “pop out”1, 2. This definition suggests that to find texture | ||
+ | we first extract certain basic features and compute their local statistics. Then we compute a measure of saliency, or degree to | ||
+ | which each portion of the image seems to be an outlier to the local feature distribution, and label as texture the regions with | ||
+ | low saliency. We present a method, based upon this idea, for labeling points in natural scenes as belonging to texture | ||
+ | regions. This method is based upon recent psychophysics results on processing of texture and popout. | ||
+ | |||
+ | The pdf included here is actually from SPIE '99, a similar extended abstract. | ||
+ | |||
+ | =====Information===== | ||
---- dataentry pubitem ---- | ---- dataentry pubitem ---- | ||
Line 4: | Line 23: | ||
authors : R. Rosenholtz | authors : R. Rosenholtz | ||
citation : Advances in Neural Information Processing Systems, 11, M. S. Kearns, S. A. Solla , & D. A. Cohn (eds.), MIT Press, Cambridge, MA | citation : Advances in Neural Information Processing Systems, 11, M. S. Kearns, S. A. Solla , & D. A. Cohn (eds.), MIT Press, Cambridge, MA | ||
- | shortcite : | + | shortcite : NIPS |
year : 1999 | year : 1999 | ||
created_dt : 1999-01-01 | created_dt : 1999-01-01 | ||
- | keyword_tags : rosenholtz | + | summary_page : publications:localtexture99 |
+ | keyword_tags : rosenholtz, visstat | ||
www_url : | www_url : | ||
- | pdf_url : | + | pdf_url : http://persci.mit.edu/_media/pub_pdfs/RosenholtzFindingTextureSPIE99.pdf |
pageid : localtexture99 | pageid : localtexture99 | ||
type : publication | type : publication | ||
---- | ---- | ||
- | |||
- |