Embedded double matching of local descriptors for a fast automatic recognition of real-world objects

T. Alqaisi, D. Gledhill, J.I. Olszewska

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Citations (Scopus)

Abstract

In this paper, we present a new approach for matching local descriptors such as Scale Invariant Feature Transform (SIFT) ones in order to recognize image objects quickly and reliably. The proposed method first computes the Hausdorff distance combined with the City-Block distance to match the two sets of the extracted keypoints from the goal and data images, respectively. Then, the matched points are involved into an embedded pairing process, leading to a double matching which is more discriminant for the object recognition purpose as demonstrated on real-world standard databases.
Original languageEnglish
Title of host publication 2012 19th IEEE International Conference on Image Processing
PublisherIEEE
Pages2385-2388
Number of pages4
ISBN (Electronic)9781467325332
ISBN (Print)9781467325349
DOIs
Publication statusPublished - 21 Feb 2013
Externally publishedYes

Publication series

NameIEEE Conference Proceedings
PublisherIEEE
ISSN (Print)1522-4880
ISSN (Electronic)2381-8549

Keywords

  • object recognition
  • feature extraction
  • robustness
  • computer vision
  • databases
  • conferences
  • Euclidean distance

Fingerprint

Dive into the research topics of 'Embedded double matching of local descriptors for a fast automatic recognition of real-world objects'. Together they form a unique fingerprint.

Cite this