Learning Discriminative and Transformation Covariant Local Feature Detectors
Authors:
- Xu ZhangXZXu Zhang
- Felix X. YuFYFelix X. Yu
- Svebor KaramanSKSvebor Karaman
- Shih-Fu ChangSCShih-Fu Chang
- 1 July 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 4923-4931
Abstract
Robust covariant local feature detectors are important for detecting local features that are (1) discriminative of the image content and (2) can be repeatably detected at consistent locations when the image undergoes diverse transformations. Such detectors are critical for applications such as image search and scene reconstruction. Many learning-based local feature detectors address one of these two problems while overlooking the other. In this work, we propose a novel learning-based method to simultaneously address both issues. Specifically, we extend the covariant constraint proposed by Lenc and Vedaldi [8] by defining the concepts of standard patch and canonical feature and leverage these to train a novel robust covariant detector. We show that the introduction of these concepts greatly simplifies the learning stage of the covariant detector, and also makes the detector much more robust. Extensive experiments show that our method outperforms previous hand-crafted and learning-based detectors by large margins in terms of repeatability.Keywords
This publication has 22 references indexed in Scilit:
- Edge foci interest points2011
- Evolutionary-computer-assisted design of image operators that detect interest points using genetic programmingImage and Vision Computing, 2011
- ASIFT: A New Framework for Fully Affine Invariant Image ComparisonSIAM Journal on Imaging Sciences, 2009
- An A Contrario Decision Method for Shape Element RecognitionInternational Journal of Computer Vision, 2006
- A Comparison of Affine Region DetectorsInternational Journal of Computer Vision, 2005
- A performance evaluation of local descriptorsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Scale & Affine Invariant Interest Point DetectorsInternational Journal of Computer Vision, 2004
- Robust wide-baseline stereo from maximally stable extremal regionsImage and Vision Computing, 2004
- Indexing based on scale invariant interest points2001
- A Combined Corner and Edge Detector1988