Best-Buddies Similarity - Robust Template Matching using Mutual Nearest Neighbors
Preprint
Abstract
We propose a novel method for template matching in unconstrained environments. Its essence is the Best-Buddies Similarity (BBS), a useful, robust, and parameter-free similarity measure between two sets of points. BBS is based on counting the number of Best-Buddies Pairs (BBPs)--pairs of points in source and target sets, where each point is the nearest neighbor of the other. BBS has several key features that make it robust against complex geometric deformations and high levels of outliers, such as those arising from background clutter and occlusions. We study these properties, provide a statistical analysis that justifies them, and demonstrate the consistent success of BBS on a challenging real-world dataset while using different types of features.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Fast-Match: Fast Affine Template MatchingInternational Journal of Computer Vision, 2016
- Image Matching Using Mutual k-Nearest Neighbor Graph2015
- Locally Orderless TrackingInternational Journal of Computer Vision, 2014
- Clustering algorithm based on mutual K‐nearest neighbor relationshipsStatistical Analysis and Data Mining: An ASA Data Science Journal, 2012
- Globally Optimal Estimation of Nonrigid Image DistortionInternational Journal of Computer Vision, 2011
- Grayscale Template-Matching Invariant to Rotation, Scale, Translation, Brightness and Contrast2007
- Real-time tracking of non-rigid objects using mean shift2002
- Shape matching and object recognition using shape contextsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Rotation-invariant pattern matching using wavelet decompositionPattern Recognition Letters, 2002
- The Earth Mover's Distance as a Metric for Image RetrievalInternational Journal of Computer Vision, 2000