A comparison of feature detectors and descriptors for object class matching

Antti Hietanen, Jukka Lankinen, Joni-Kristian Kämäräinen, Anders Glent Buch, Norbert Krüger

Research output: Contribution to journalConference articleResearchpeer-review

Abstract

Solid protocols to benchmark local feature detectors and descriptors were introduced by Mikolajczyk et al. [1,2]. The detectors and the descriptors are popular tools in object class matching, but the wide baseline setting in the benchmarks does not correspond to class-level matching where appearance variation can be large. We extend the benchmarks to the class matching setting and evaluate state-ofthe- art detectors and descriptors with Caltech and ImageNet classes. Our experiments provide important findings with regard to object class matching: (1) the original SIFT is still the best descriptor; (2) dense sampling outperforms interest point detectors with a clear margin; (3) detectors perform moderately well, but descriptors' performance collapses; (4) using multiple, even a few, best matches instead of the single best has significant effect on the performance; (5) object pose variation degrades dense sampling performance while the best detector (Hessian-affine) is unaffected. The performance of the best detectordescriptor pair is verified in the application of unsupervised visual class alignment where state-of-the-art results are achieved. The findings help to improve the existing detectors and descriptors for which the framework provides an automatic validation tool.

Original languageEnglish
JournalNeurocomputing
Volume184
Issue numberC
Pages (from-to)3-12
ISSN0925-2312
DOIs
Publication statusPublished - 2016
EventRobust Local Descriptors for Computer Vision - , Singapore
Duration: 1. Nov 20145. Nov 2016

Conference

ConferenceRobust Local Descriptors for Computer Vision
Country/TerritorySingapore
Period01/11/201405/11/2016

Keywords

  • BRIEF
  • Interest point
  • Local descriptor
  • Local detector
  • SIFT
  • SURF

Fingerprint

Dive into the research topics of 'A comparison of feature detectors and descriptors for object class matching'. Together they form a unique fingerprint.

Cite this