Best-Buddies Similarity - Robust Template Matching using Mutual Nearest Neighbors
This addresses robust template matching for computer vision applications, offering a novel approach to handle deformations and outliers, but it is incremental as it builds on nearest-neighbor concepts.
The paper tackles template matching in unconstrained environments by proposing Best-Buddies Similarity (BBS), a robust and parameter-free measure based on mutual nearest neighbors, and demonstrates its consistent success on a challenging real-world dataset with various features.
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.