Evaluation of Gradient Vector Flow for Interest Point Detection

Authors:
Julian Stöttinger;René Donner;Lech Szumilas;Allan Hanbury
Affiliations:
PRIP, Vienna University of Technology, Austria;PRIP, Vienna University of Technology, Austria and ICG, Technical University Graz, Austria and CIR, Vienna Medical University, Austria;ACIN, Vienna University of Technology, Austria;PRIP, Vienna University of Technology, Austria
Venue:
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing
Year:
2008

Citing 8
Cited 1

Context-free attentional operators: the generalized symmetry transform

International Journal of Computer Vision - Special issue on qualitative vision
Feature Detection with Automatic Scale Selection

International Journal of Computer Vision
An Affine Invariant Interest Point Detector

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
A Fast Radial Symmetry Transform for Detecting Points of Interest

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Fast Radial Symmetry for Detecting Points of Interest

IEEE Transactions on Pattern Analysis and Machine Intelligence
Scale & Affine Invariant Interest Point Detectors

International Journal of Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Scale-space filtering

IJCAI'83 Proceedings of the Eighth international joint conference on Artificial intelligence - Volume 2

Efficient numerical schemes for gradient vector flow

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present and evaluate an approach for finding local interest points in images based on the non-minima suppression of Gradient Vector Flow (GVF) magnitude. Based on the GVF's properties it provides the approximate centers of blob-like structures or homogeneous structures confined by gradients of similar magnitude. It results in a scale and orientation invariant interest point detector, which is highly stable against noise and blur. These interest points outperform the state of the art detectors in various respects. We show that our approach gives a dense and repeatable distribution of locations that are robust against affine transformations while they outperform state of the art techniques in robustness against lighting changes, noise, rotation and scale changes. Extensive evaluation is carried out using the Mikolajcyzk framework for interest point detector evaluation.