Skip to Main content Skip to Navigation
Conference papers

The High Repeatability of Salient Regions

Abstract : In this paper, we show that salient regions, detected by a biologically motivated attention system, have a considerably higher repeatability than features detected by standard detectors (Harris-Laplacians and DoG features). If a scene contains a salient region, which differs in one of several possible features from the rest of the scene, the repeatability is close to 100%. In settings in which no especially salient region is present, the repeatability of attention regions is similar to DoG features and considerably higher than Harris-Laplacians.
Document type :
Conference papers
Complete list of metadata

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/inria-00325799
Contributor : Peter Sturm <>
Submitted on : Tuesday, September 30, 2008 - 1:29:40 PM
Last modification on : Thursday, February 7, 2019 - 4:33:47 PM
Long-term archiving on: : Monday, October 8, 2012 - 1:45:14 PM

File

Frintrop.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00325799, version 1

Collections

Citation

Simone Frintrop. The High Repeatability of Salient Regions. Workshop on Vision in Action: Efficient strategies for cognitive agents in complex environments, Markus Vincze and Danica Kragic and Darius Burschka and Antonis Argyros, Oct 2008, Marseille, France. ⟨inria-00325799⟩

Share

Metrics

Record views

138

Files downloads

263