Learning Covariant Feature Detectors
Authors:
Preprint
Abstract
Local covariant feature detection, namely the problem of extracting viewpoint invariant features from images, has so far largely resisted the application of machine learning techniques. In this paper, we propose the first fully general formulation for learning local covariant feature detectors. We propose to cast detection as a regression problem, enabling the use of powerful regressors such as deep neural networks. We then derive a covariance constraint that can be used to automatically learn which visual structures provide stable anchors for local feature detection. We support these ideas theoretically, proposing a novel analysis of local features in term of geometric transformations, and we show that all common and many uncommon detectors can be derived in this framework. Finally, we present empirical results on a variety of detector types and on standard feature benchmarks, showing the power and flexibility of the framework.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Interesting Interest PointsInternational Journal of Computer Vision, 2011
- Evolutionary-computer-assisted design of image operators that detect interest points using genetic programmingImage and Vision Computing, 2011
- Learning a Fast Emulator of a Binary Decision Process2007
- A Wavelet Tour of Signal Processing1999
- SUSAN—A New Approach to Low Level Image ProcessingInternational Journal of Computer Vision, 1997
- Scale-Space Theory in Computer Vision1994
- Shape-adapted smoothing in estimation of 3-D depth cues from affine distortions of local 2-D brightness structure1994
- Recognizing corners by fitting parametric modelsInternational Journal of Computer Vision, 1992
- Corner characterization by differential geometry techniquesPattern Recognition Letters, 1988
- A parallel procedure for the detection of dominant points on a digital curveComputer Graphics and Image Processing, 1978