Learning Local Image Descriptors
Top Cited Papers
- 1 June 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1-8
- https://doi.org/10.1109/cvpr.2007.382971
Abstract
In this paper we study interest point descriptors for image matching and 3D reconstruction. We examine the building blocks of descriptor algorithms and evaluate numerous combinations of components. Various published descriptors such as SIFT, GLOH, and Spin images can be cast into our framework. For each candidate algorithm we learn good choices for parameters using a training set consisting of patches from a multi-image 3D reconstruction where accurate ground-truth matches are known. The best descriptors were those with log polar histogramming regions and feature vectors constructed from rectified outputs of steerable quadrature filters. At a 95% detection rate these gave one third of the incorrect matches produced by SIFT.Keywords
This publication has 15 references indexed in Scilit:
- Scalable Recognition with a Vocabulary TreePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Photo tourismACM Transactions on Graphics, 2006
- A performance evaluation of local descriptorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Shape Matching and Object Recognition Using Low Distortion CorrespondencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Multi-Image Matching Using Multi-Scale Oriented PatchesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Evaluation of features detectors and descriptors based on 3D objectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Shape matching and object recognition using shape contextsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- From images to 3D modelsCommunications of the ACM, 2002
- Indexing based on scale invariant interest pointsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Filtering for texture classification: a comparative studyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999