Detecting distinguished regions by saliency

Authors:
Friedrich Fraundorfer;Horst Bischof
Affiliations:
Computer Graphics and Vision, Graz University of Technology, Austria;Computer Graphics and Vision, Graz University of Technology, Austria
Venue:
SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
Year:
2003

Citing 5
Cited 4

Texture Features for Browsing and Retrieval of Image Data

IEEE Transactions on Pattern Analysis and Machine Intelligence
Local Grayvalue Invariants for Image Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence
Evaluation of Interest Point Detectors

International Journal of Computer Vision - Special issue on a special section on visual surveillance
Saliency, Scale and Image Description

International Journal of Computer Vision
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2

Robust Complex Salient Regions

IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part II
Image description with features that summarize

Computer Vision and Image Understanding
Piecewise planar scene reconstruction from sparse correspondences

Image and Vision Computing
Robust homography-based control for camera positioning in piecewise planar environments

ICVGIP'06 Proceedings of the 5th Indian conference on Computer Vision, Graphics and Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A method for detecting and characterizing local image regions based on saliency is introduced. The proposed method detects scale localized salient regions in an image by a saliency operator which uses the concept of visual attention. A new descriptor based on a cornerness measure is presented which allows a stable identification of regions of interest and at the same time allows for an elaborate description of the identified salient regions. Experiments demonstrate that the resulting salient regions and their descriptions are discriminative enough for image matching.