Co-Segmentation Guided Hough Transform for Robust Feature Matching

Hsin Yi Chen, Yen-Yu Lin, Bing Yu Chen

Research output: Contribution to journalArticle

24 Scopus citations

Abstract

We present an algorithm that integrates image co-segmentation into feature matching, and can robustly yield accurate and dense feature correspondences. Inspired by the fact that correct feature correspondences on the same object typically have coherent transformations, we cast the task of feature matching as a density estimation problem in the homography space. Specifically, we project the homographies of correspondence candidates into the parametric Hough space, in which geometric verification of correspondences can be activated by voting. The precision of matching is then boosted. On the other hand, we leverage image co-segmentation, which discovers object boundaries, to determine relevant voters and speed up Hough voting. In addition, correspondence enrichment can be achieved by inferring the concerted homographies that are propagated between the features within the same segments. The recall is hence increased. In our approach, feature matching and image co-segmentation are tightly coupled. Through an iterative optimization process, more and more correct correspondences are detected owing to object boundaries revealed by co-segmentation. The proposed approach is comprehensively evaluated. Promising experimental results on four datasets manifest its effectiveness.

Original languageEnglish
Article number7080945
Pages (from-to)2388-2401
Number of pages14
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume37
Issue number12
DOIs
StatePublished - 1 Dec 2015

Keywords

  • Hough transform
  • Image feature matching
  • co-segmentation
  • correspondence problems
  • energy minimization

Fingerprint Dive into the research topics of 'Co-Segmentation Guided Hough Transform for Robust Feature Matching'. Together they form a unique fingerprint.

  • Cite this