Matching Images with Multiple Descriptors: An Unsupervised Approach for Locally Adaptive Descriptor Selection

Yuan Ting Hu, Yen-Yu Lin, Hsin Yi Chen, Kuang Jui Hsu, Bing Yu Chen

Research output: Contribution to journalArticlepeer-review

19 Scopus citations

Abstract

With the aim to improve the performance of feature matching, we present an unsupervised approach for adaptive description selection in the space of homographies. Inspired by the observation that the homographies of correct feature correspondences vary smoothly along the spatial domain, our approach stands on the unsupervised nature of feature matching, and can choose a good descriptor locally for matching each feature point, instead of using one global descriptor. To this end, the homography space serves as the domain for selecting various heterogeneous descriptors. Correspondences obtained by any descriptors are considered as points in the space, and their geometric coherence and spatial continuity are measured via computing the geodesic distances. In this way, mutual verification across different descriptors is allowed, and correct correspondences will be highlighted with a high degree of consistency short geodesic distances here. It follows that one-class SVM can be applied to identifying these correct correspondences, and achieves adaptive descriptor selection. The proposed approach is comprehensively compared with the state-of-the-art approaches, and evaluated on five benchmarks of image matching. The promising results manifest its effectiveness.

Original languageEnglish
Article number7312974
Pages (from-to)5995-6010
Number of pages16
JournalIEEE Transactions on Image Processing
Volume24
Issue number12
DOIs
StatePublished - 1 Dec 2015

Keywords

  • descriptor selection
  • geodesic distance
  • geometric verification
  • homography space
  • Image feature matching
  • One class SVM

Fingerprint Dive into the research topics of 'Matching Images with Multiple Descriptors: An Unsupervised Approach for Locally Adaptive Descriptor Selection'. Together they form a unique fingerprint.

Cite this