Efficient Image Matching with Distributions of Local Invariant Features

  • Authors:
  • Kristen Grauman;Trevor Darrell

  • Affiliations:
  • Massachusetts Institute of Technology;Massachusetts Institute of Technology

  • Venue:
  • CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Sets of local features that are invariant to common image transformations are an effective representation to use when comparing images; current methods typically judge feature setsý similarity via a voting scheme (which ignores co-occurrence statistics) or by comparing histograms over a set of prototypes (which must be found by clustering). We present a method for efficiently comparing images based on their discrete distributions (bags) of distinctive local invariant features, without clustering descriptors. Similarity between images is measured with an approximation of the Earth Moverýs Distance (EMD), which quickly computes minimal-cost correspondences between two bags of features. Each imageýs feature distribution is mapped into a normed space with a low-distortion embedding of EMD. Examples most similar to a novel query image are retrieved in time sublinear in the number of examples via approximate nearest neighbor search in the embedded space. We evaluate our method with scene, object, and texture recognition tasks.