Best-Buddies Similarity - Robust Template Matching using Mutual Nearest Neighbors

TL;DR

The paper introduces Best-Buddies Similarity (BBS), a robust, parameter-free measure for template matching that effectively handles geometric deformations and outliers in unconstrained environments.

Contribution

It presents a novel similarity measure based on mutual nearest neighbors, with theoretical analysis and demonstrated success on real-world datasets.

Findings

BBS is robust against geometric deformations.

BBS effectively handles high levels of outliers.

BBS achieves consistent success in real-world template matching.

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.