Best-Buddies Similarity—Robust Template Matching Using Mutual Nearest Neighbors
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 s...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2019
|
| Online Access: | https://hdl.handle.net/1721.1/121575 |
| _version_ | 1826216637854908416 |
|---|---|
| author | Oron, Shaul Dekel, Tali Xue, Tianfan Freeman, William T. Avidan, Shai |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Oron, Shaul Dekel, Tali Xue, Tianfan Freeman, William T. Avidan, Shai |
| author_sort | Oron, Shaul |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T16:51:01Z |
| format | Article |
| id | mit-1721.1/121575 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T16:51:01Z |
| publishDate | 2019 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1215752022-10-03T08:42:19Z Best-Buddies Similarity—Robust Template Matching Using Mutual Nearest Neighbors Oron, Shaul Dekel, Tali Xue, Tianfan Freeman, William T. Avidan, Shai Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 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. Israel Science Foundation (Grant 1917/2015) National Science Foundation (U.S.) (1212849) Shell Research 2019-07-10T18:13:28Z 2019-07-10T18:13:28Z 2018-08-01 2019-05-28T14:46:04Z Article http://purl.org/eprint/type/JournalArticle 0162-8828 2160-9292 1939-3539 https://hdl.handle.net/1721.1/121575 Oron, Shaul, et al. “Best-Buddies Similarity—Robust Template Matching Using Mutual Nearest Neighbors.” IEEE Transactions on Pattern Analysis and Machine Intelligence 40, no. 8 (August 2018): 1799–813. © 2017 IEEE. en 10.1109/tpami.2017.2737424 IEEE Transactions on Pattern Analysis and Machine Intelligence Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Oron, Shaul Dekel, Tali Xue, Tianfan Freeman, William T. Avidan, Shai Best-Buddies Similarity—Robust Template Matching Using Mutual Nearest Neighbors |
| title | Best-Buddies Similarity—Robust Template Matching Using Mutual Nearest Neighbors |
| title_full | Best-Buddies Similarity—Robust Template Matching Using Mutual Nearest Neighbors |
| title_fullStr | Best-Buddies Similarity—Robust Template Matching Using Mutual Nearest Neighbors |
| title_full_unstemmed | Best-Buddies Similarity—Robust Template Matching Using Mutual Nearest Neighbors |
| title_short | Best-Buddies Similarity—Robust Template Matching Using Mutual Nearest Neighbors |
| title_sort | best buddies similarity robust template matching using mutual nearest neighbors |
| url | https://hdl.handle.net/1721.1/121575 |
| work_keys_str_mv | AT oronshaul bestbuddiessimilarityrobusttemplatematchingusingmutualnearestneighbors AT dekeltali bestbuddiessimilarityrobusttemplatematchingusingmutualnearestneighbors AT xuetianfan bestbuddiessimilarityrobusttemplatematchingusingmutualnearestneighbors AT freemanwilliamt bestbuddiessimilarityrobusttemplatematchingusingmutualnearestneighbors AT avidanshai bestbuddiessimilarityrobusttemplatematchingusingmutualnearestneighbors |