Faculty of Informatics Vienna University of Technology Institute of Computer Aided Automation PRIP Home PRIP Home
Personal tools
You are here: Home People Julian Stöttinger GVFpoints

Evaluation of Gradient Vector Flow for Interest Point Detection

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.

For results and method, please refer to

Evaluation of Gradient Vector Flow for Interest Point Detection

Julian Stöttinger, René Donner, Lech Szumilas, Allan Hanbury, Proceedings of the 4th International Symposium on Visual Computing (ISVC), Las Vegas, Nevada, USA, December 1-3, 2008.

Download MATLAB source

The source code is available at René Donner's webpage.

Download the software package. You'll find the code under interestPoints/symPoints.