This shows you the differences between two versions of the page.
|
publications:textureeccv00 [2010/06/09 15:48] 127.0.0.1 external edit |
publications:textureeccv00 [2012/04/20 11:59] (current) rosenholtz |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| + | ====== Significantly different textures: A computational model of pre-attentive texture segmentation ====== | ||
| + | ==== Ruth Rosenholtz ==== | ||
| + | ---- | ||
| + | |||
| + | ===== Abstract ===== | ||
| + | Recent human vision research suggests modelling preattentive texture segmentation by taking a set of feature samples from a | ||
| + | local region on each side of a hypothesized edge, and then performing | ||
| + | standard statistical tests to determine if the two samples differ significantly | ||
| + | in their mean or variance. If the difference is significant at a specified level | ||
| + | of confidence, a human observer will tend to pre-attentively see a texture | ||
| + | edge at that location. I present an algorithm based upon these results, with a | ||
| + | well specified decision stage and intuitive, easily fit parameters. Previous | ||
| + | models of pre-attentive texture segmentation have poorly specified decision | ||
| + | stages, more unknown free parameters, and in some cases incorrectly model | ||
| + | human performance. The algorithm uses heuristics for guessing the | ||
| + | orientation of a texture edge at a given location, thus improving | ||
| + | computational efficiency by performing the statistical tests at only one | ||
| + | orientation for each spatial location. | ||
| + | |||
| + | ===== Information ===== | ||
| ---- dataentry pubitem ---- | ---- dataentry pubitem ---- | ||
| - | title : Significantly different textures: A computational model of pre-attentive te xture segmentation | + | title : Significantly different textures: A computational model of pre-attentive texture segmentation |
| authors : R. Rosenholtz | authors : R. Rosenholtz | ||
| citation : Proc. European Conference on Computer Vision, D. Vernon (Ed.), Springer Ver lag, LNCS 1843, Dublin, Ireland, pp. 197-211 | citation : Proc. European Conference on Computer Vision, D. Vernon (Ed.), Springer Ver lag, LNCS 1843, Dublin, Ireland, pp. 197-211 | ||
| Line 7: | Line 27: | ||
| year : 2000 | year : 2000 | ||
| created_dt : 2000-01-01 | created_dt : 2000-01-01 | ||
| + | summary_page : publications:textureeccv00 | ||
| keyword_tags : rosenholtz | keyword_tags : rosenholtz | ||
| www_url : | www_url : | ||
| Line 13: | Line 34: | ||
| type : publication | type : publication | ||
| ---- | ---- | ||
| - | |||
| - | |||