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

Shaul Oron; Tali Dekel; Tianfan Xue; William T. Freeman; Shai Avidan

doi:https://doi.org/10.1109/TPAMI.2017.2737424

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

Shaul Oron, Tali Dekel, Tianfan Xue, William T. Freeman, Shai Avidan

School of Electrical Engineering

Tel Aviv University

Research output: Contribution to journal › Article › peer-review

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 that are mutual nearest neighbours, i.e., each point is the nearest neighbour 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.

Original language	English
Pages (from-to)	1799-1813
Number of pages	15
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	40
Issue number	8
DOIs	https://doi.org/10.1109/TPAMI.2017.2737424
State	Published - 1 Aug 2018

Keywords

Best buddies
mutual nearest neighbors
non-rigid matching
point set similarity
template matching

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition
Computational Theory and Mathematics
Artificial Intelligence
Applied Mathematics

Access to Document

https://doi.org/10.1109/TPAMI.2017.2737424

Cite this

@article{3d8c7558b920480a9c79642e0f391fee,

title = "Best-Buddies Similarity - Robust Template Matching Using Mutual Nearest Neighbors",

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 that are mutual nearest neighbours, i.e., each point is the nearest neighbour 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 = "Best buddies, mutual nearest neighbors, non-rigid matching, point set similarity, template matching",

author = "Shaul Oron and Tali Dekel and Tianfan Xue and Freeman, {William T.} and Shai Avidan",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.",

year = "2018",

month = aug,

day = "1",

doi = "https://doi.org/10.1109/TPAMI.2017.2737424",

language = "الإنجليزيّة",

volume = "40",

pages = "1799--1813",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "8",

}

TY - JOUR

T1 - Best-Buddies Similarity - Robust Template Matching Using Mutual Nearest Neighbors

AU - Oron, Shaul

AU - Dekel, Tali

AU - Xue, Tianfan

AU - Freeman, William T.

AU - Avidan, Shai

PY - 2018/8/1

Y1 - 2018/8/1

N2 - 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 that are mutual nearest neighbours, i.e., each point is the nearest neighbour 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.

AB - 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 that are mutual nearest neighbours, i.e., each point is the nearest neighbour 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.

KW - Best buddies

KW - mutual nearest neighbors

KW - non-rigid matching

KW - point set similarity

KW - template matching

UR - http://www.scopus.com/inward/record.url?scp=85028448953&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/TPAMI.2017.2737424

DO - https://doi.org/10.1109/TPAMI.2017.2737424

M3 - مقالة

SN - 0162-8828

VL - 40

SP - 1799

EP - 1813

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 8

ER -

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

Abstract

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this