We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Hough Pyramid Matching: Speeded-Up Geometry Re-ranking for Large Scale Image Retrieval.
- Authors
Avrithis, Yannis; Tolias, Giorgos
- Abstract
Exploiting local feature shape has made geometry indexing possible, but at a high cost of index space, while a sequential spatial verification and re-ranking stage is still indispensable for large scale image retrieval. In this work we investigate an accelerated approach for the latter problem. We develop a simple spatial matching model inspired by Hough voting in the transformation space, where votes arise from single feature correspondences. Using a histogram pyramid, we effectively compute pair-wise affinities of correspondences without ever enumerating all pairs. Our Hough pyramid matching algorithm is linear in the number of correspondences and allows for multiple matching surfaces or non-rigid objects under one-to-one mapping. We achieve re-ranking one order of magnitude more images at the same query time with superior performance compared to state of the art methods, while requiring the same index space. We show that soft assignment is compatible with this matching scheme, preserving one-to-one mapping and further increasing performance.
- Subjects
IMAGE retrieval; HOUGH functions; MATHEMATICAL transformations; ALGORITHMS; HISTOGRAMS
- Publication
International Journal of Computer Vision, 2014, Vol 107, Issue 1, p1
- ISSN
0920-5691
- Publication type
Article
- DOI
10.1007/s11263-013-0659-3