{"type":"ScholarlyArticle","title":"Locality Preserving Matching","authors":[{"name":"Jiayi Ma","slug":"jiayi-ma","given":"Jiayi","family":"Ma","affiliation":"* Electronic Information School , Wuhan University , Wuhan 430072 , China"},{"name":"Ji Zhao","slug":"ji-zhao","given":"Ji","family":"Zhao","affiliation":"* Electronic Information School , Wuhan University , Wuhan 430072 , China"},{"name":"Hanqi Guo","slug":"hanqi-guo","given":"Hanqi","family":"Guo","affiliation":"* Electronic Information School , Wuhan University , Wuhan 430072 , China"},{"name":"Junjun Jiang","slug":"junjun-jiang","given":"Junjun","family":"Jiang","affiliation":"† School of Computer Science , China University of Geosciences , Wuhan 430074 , China"},{"name":"Huabing Zhou","slug":"huabing-zhou","given":"Huabing","family":"Zhou","affiliation":"‡ School of Computer Science and Engineering , Wuhan Institute of Technology , Wuhan 430073 , China"},{"name":"Yuan Gao","slug":"yuan-gao","given":"Yuan","family":"Gao","affiliation":"§ Tencent AI Laboratory , Shenzhen 518057 , China"}],"abstract":"Seeking reliable correspondences between two feature sets is a fundamental and important task in computer vision. This paper attempts to remove mismatches from given putative image feature correspondences. To achieve the goal, an efficient approach, termed as locality preserving matching (LPM), is designed, the principle of which is to maintain the local neighborhood structures of those potential true matches. We formulate the problem into a mathematical model, and derive a closed-form solution with linearithmic time and linear space complexities. More specifically, our method can accomplish the mismatch removal from thousands of putative correspondences in only a few milliseconds. Experiments on various real image pairs for general feature matching, as well as for visual homing and image retrieval demonstrate the generality of our method for handling different types of image deformations, and it is more than two orders of magnitude faster than state-of-the-art methods in the same range of or better accuracy.","doi":"10.24963/ijcai.2017/627","url":"https://ijcai.org/proceedings/2017/627","pdf":"https://ijcai.org/proceedings/2017/0627.pdf","markdown":"https://ijcai.org/proceedings/2017/627.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/627","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Robotics and Vision","track":"Main track","number":627,"pages":{"first":4492,"last":4498},"keywords":["Robotics and Vision: Robotics and Vision","Robotics and Vision: Localization, Mapping, State Estimation"],"videos":[],"references":[{"position":1,"raw":"[Bai et al., 2010] Xiang Bai, Xingwei Yang, Longin Jan Latecki, Wenyu Liu, and Zhuowen Tu. Learning context- sensitive shape similarity by graph transduction. IEEE Trans. Pattern Anal. Mach. Intell., 32(5):861-874, 2010.","title":"Learning contextsensitive shape similarity by graph transduction","authors":"Xiang Bai, Xingwei Yang, Longin, Jan Latecki, Wenyu Liu, Zhuowen Tu","year":"2010","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bai et al., 2017] Song Bai, Xiang Bai, and Qi Tian. Scalable person re-identification on supervised smoothed manifold. In CVPR, 2017.","title":"Scalable person re-identification on supervised smoothed manifold","authors":"Song Bai, Xiang Bai, Qi Tian","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bentley, 1975] Jon Louis Bentley. Multidimensional bina- ry search trees used for associative searching. Commun. ACM, 18(9):509-517, 1975.","title":"Multidimensional binary search trees used for associative searching","authors":"Jon Louis Bentley, Bentley","year":"1975","venue":"Commun. ACM","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cho and Lee, 2012] Minsu Cho and Kyoung Mu Lee. Pro- gressive graph matching: Making a move of graphs via probabilistic voting. In CVPR, pages 398-405, 2012.","title":"Progressive graph matching: Making a move of graphs via probabilistic voting","authors":"Lee ; ] Minsu Cho, Kyoung Cho, Lee Mu","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chum and Matas, 2005] Ondrej Chum and Jiri Matas. Matching with PROSAC -progressive sample consensus. In CVPR, pages 220-226, 2005.","title":"Matching with PROSAC -progressive sample consensus","authors":"Matas Chum, Ondrej Chum, Jiri Matas","year":"2005","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Churchill and Vardy, 2013] David Churchill and Andrew Vardy. An orientation invariant visual homing algorithm. J. Intell. Robot. Syst., 71(1):3-29, 2013.","title":"An orientation invariant visual homing algorithm","authors":"Churchill, Vardy, David Churchill, Andrew Vardy","year":"2013","venue":"J. Intell. Robot. Syst","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fischler and Bolles, 1981] Martin A Fischler and Robert C Bolles. Random sample consensus: A paradigm for model fitting with application to image analysis and automated cartography. Commun. ACM, 24(6):381-395, 1981.","title":"Random sample consensus: A paradigm for model fitting with application to image analysis and automated cartography","authors":"A Martin, Robert C Fischler, Bolles","year":"1981","venue":"Commun. ACM","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Guo and Cao, 2012] Xiaojie Guo and Xiaochun Cao. Good match exploration using triangle constraint. Pattern Recognit. Lett., 33(7):872-881, 2012.","title":"Good match exploration using triangle constraint","authors":"Xiaojie Guo, Xiaochun Cao","year":"2012","venue":"Pattern Recognit. Lett","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hu et al., 2015] Yuan-Ting Hu, Yen-Yu Lin, Hsin-Yi Chen, Kuang-Jui Hsu, and Bing-Yu Chen. Matching images with multiple descriptors: An unsupervised approach for local- ly adaptive descriptor selection. IEEE Trans. Image Pro- cess., 24(12):5995-6010, 2015.","title":"Matching images with multiple descriptors: An unsupervised approach for locally adaptive descriptor selection","authors":"Yuan-Ting Hu, Yen-Yu Lin, Hsin-Yi Chen, Kuang-Jui Hsu, Bing-Yu Chen","year":"2015","venue":"IEEE Trans. Image Process","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Huber, 1981] Peter J Huber. Robust Statistics. John Wiley & Sons, New York, 1981.","title":"Robust Statistics","authors":"J Peter, Huber","year":"1981","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jinda-Apiraksa et al., 2013] Amornched Jinda-Apiraksa, Vassilios Vonikakis, and Stefan Winkler. California-ND: An annotated dataset for near-duplicate detection in personal photo collections. In QoMEX, pages 142-147, 2013.","title":"Amornched Jinda-Apiraksa, Vassilios Vonikakis, and Stefan Winkler. California-ND: An annotated dataset for near-duplicate detection in personal photo collections","authors":"Jinda-Apiraksa","year":"2013","venue":"QoMEX","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lee et al., 2015] Man Hee Lee, Minsu Cho, and In Kyu Park. Feature description using local neighborhoods. Pat- tern Recognit. Lett., 68:76-82, 2015.","title":"Feature description using local neighborhoods","authors":"Lee","year":"2015","venue":"Pattern Recognit. Lett","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Leordeanu and Hebert, 2005] Marius Leordeanu and Mar- tial Hebert. A spectral technique for correspondence prob- lems using pairwise constraints. In ICCV, pages 1482- 1489, 2005.","title":"Marius Leordeanu and Martial Hebert. A spectral technique for correspondence problems using pairwise constraints","authors":"Hebert Leordeanu","year":"2005","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li and Hu, 2010] Xiangru Li and Zhanyi Hu. Rejecting mismatches by correspondence function. Int. J. Comput. Vis., 89(1):1-17, 2010.","title":"Xiangru Li and Zhanyi Hu. Rejecting mismatches by correspondence function","authors":"Hu Li","year":"2010","venue":"Int. J. Comput. Vis","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liu and Yan, 2010] Hairong Liu and Shuicheng Yan. Com- mon visual pattern discovery via spatially coherent corre- spondence. In CVPR, pages 1609-1616, 2010.","title":"Common visual pattern discovery via spatially coherent correspondence","authors":"Yan ; ] Hairong Liu, Shuicheng Liu, Yan","year":"2010","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu et al., 2013] Ming Liu, Cedric Pradalier, and Roland Siegwart. Visual homing from scale with an uncali- brated omnidirectional camera. IEEE Trans. Robotics, 29(6):1353-1365, 2013.","title":"Visual homing from scale with an uncalibrated omnidirectional camera","authors":"Liu","year":"2013","venue":"IEEE Trans. Robotics","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liu et al., 2015] Yonghuai Liu, Luigi De Dominicis, Bao- gang Wei, Liang Chen, and Ralph R Martin. Regular- ization based iterative point match weighting for accurate rigid transformation estimation. IEEE Trans. Vis. Comput. Graph., 21(9):1058-1071, 2015.","title":"Regularization based iterative point match weighting for accurate rigid transformation estimation","authors":"Liu","year":"2015","venue":"IEEE Trans. Vis. Comput. Graph","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Lowe, 2004] David G Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 60(2):91-110, 2004.","title":"Distinctive image features from scale-invariant keypoints","authors":"David G Lowe","year":"2004","venue":"IJCV","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ma et al., 2013] Jiayi Ma, Ji Zhao, Jinwen Tian, Zhuowen Tu, and Alan L Yuille. Robust estimation of nonrigid trans- formation for point set registration. In CVPR, pages 2147- 2154, 2013.","title":"Robust estimation of nonrigid transformation for point set registration","authors":"Jiayi Ma, Ji Zhao, Jinwen Tian, Zhuowen Tu, Alan L Yuille","year":"2013","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ma et al., 2014] Jiayi Ma, Ji Zhao, Jinwen Tian, Alan L Yuille, and Zhuowen Tu. Robust point matching via vector field consensus. IEEE Trans. Image Process., 23(4):1706- 1721, 2014.","title":"Robust point matching via vector field consensus","authors":"Jiayi Ma, Ji Zhao, Jinwen Tian, Alan L Yuille, Zhuowen Tu","year":"2014","venue":"IEEE Trans. Image Process","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ma et al., 2017] Jiayi Ma, Ji Zhao, Junjun Jiang, and Huabing Zhou. Non-rigid point set registration with ro- bust transformation estimation under manifold regulariza- tion. In AAAI, pages 4218-4224, 2017.","title":"Non-rigid point set registration with robust transformation estimation under manifold regularization","authors":"Jiayi Ma, Ji Zhao, Junjun Jiang, Huabing Zhou","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Maier et al., 2016] Josef Maier, Martin Humenberger, Markus Murschitz, Oliver Zendel, and Markus Vincze. Guided matching based on statistical optical flow for fast and robust correspondence analysis. In ECCV, pages 101-117, 2016.","title":"Guided matching based on statistical optical flow for fast and robust correspondence analysis","authors":"Maier","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Mikolajczyk et al., 2005] Krystian Mikolajczyk, Tinne Tuytelaars, Cordelia Schmid, Andrew Zisserman, Jiri Matas, Frederik Schaffalitzky, Timor Kadir, and Luc Van Gool. A comparison of affine region detectors. Int. J. Comput. Vis., 65(1):43-72, 2005.","title":"A comparison of affine region detectors","authors":"Krystian Mikolajczyk, Tinne Tuytelaars, Cordelia Schmid, Andrew Zisserman, Jiri Matas, Frederik Schaffalitzky, Timor Kadir, Luc Van Gool","year":"2005","venue":"Int. J. Comput. Vis","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Torr and Zisserman, 2000] Philip HS Torr and Andrew Zis- serman. MLESAC: A new robust estimator with applica- tion to estimating image geometry. Comput. Vis. Image Understand., 78(1):138-156, 2000.","title":"MLESAC: A new robust estimator with application to estimating image geometry","authors":"Torr Philip, Andrew Zisserman","year":"2000","venue":"Comput. Vis. Image Understand","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Torresani et al., 2008] Lorenzo Torresani, Vladimir Kol- mogorov, and Carsten Rother. Feature correspondence via graph matching: Models and global optimization. In EC- CV, pages 596-609, 2008.","title":"Feature correspondence via graph matching: Models and global optimization","authors":"Lorenzo Torresani, Vladimir Kolmogorov, Carsten Rother","year":"2008","venue":"EC-CV","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Vedaldi and Fulkerson, 2010] Andrea Vedaldi and Brian Fulkerson. VLFeat -An open and portable library of com- puter vision algorithms. In MM, pages 1469-1472, 2010.","title":"VLFeat -An open and portable library of computer vision algorithms","authors":"Fulkerson Vedaldi, Andrea Vedaldi, Brian Fulkerson","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wang et al., 2014] Chao Wang, Lei Wang, and Lingqiao Li- u. Progressive mode-seeking on graphs for sparse feature matching. In ECCV, pages 788-802, 2014.","title":"Progressive mode-seeking on graphs for sparse feature matching","authors":"Chao Wang, Lei Wang, Lingqiao Liu","year":"2014","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Wang et al., 2017] Gang Wang, Qiangqiang Zhou, and Yufei Chen. Robust non-rigid point set registration using spatially constrained gaussian fields. IEEE Trans. Image Process., 26(4):1759-1769, 2017.","title":"Robust non-rigid point set registration using spatially constrained gaussian fields","authors":"Gang Wang, Qiangqiang Zhou, Yufei Chen","year":"2017","venue":"IEEE Trans. Image Process","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zheng and Doermann, 2006] Yefeng Zheng and David Do- ermann. Robust point matching for nonrigid shapes by p- reserving local neighborhood structures. IEEE Trans. Pat- tern Anal. Mach. Intell., 28(4):643-649, 2006.","title":"Yefeng Zheng and David Doermann. Robust point matching for nonrigid shapes by preserving local neighborhood structures","authors":"Doermann Zheng","year":"2006","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}