Objects recognition using SIFT and fuzzy similarity measure

  1. (PDF, 433 KB)
AuthorSearch for: ; Search for:
ConferenceThe 20th Annual IS&T/SPIE Symposium on Electronic Imaging, January 27-31, 2008., San Jose, California, USA
SubjectSIFT descriptors; fuzzy similarity; object recognition; fuzzy triangular number; similarité floue; reconnaissance des objets; nombre triangulaire flou
AbstractMultimedia database has been an extremely active area of research over the last 20 years. This research aims to develop techniques for searching and recognizing multimedia documents based on their content. For objects recognition, make works proposed different techniques to extract the visual contents such as color, shape, texture, etc. By comparing these visual contents, we can determine whether or not the image data contains some specific object. Since the Euclidean distance has always been employed to compare visual contents so far, using other approaches for the comparison is an interesting research way that still needs to be explored. In this paper, we propose fuzzy similarity measures as alternatives for the Euclidean distance. Visual contents to be compared are based on the Scale Invariant Feature Transform (SIFT). This approach has been applied to coil databases. Our experimentation shows that this method is more realistic than objects recognition method obtained by classical distances.
Publication date
AffiliationNRC Institute for Information Technology; National Research Council Canada
Peer reviewedNo
NRC number49914
NPARC number8914130
Export citationExport as RIS
Report a correctionReport a correction
Record identifierd79cef04-eba1-4f1a-886a-a8be3c7e6c01
Record created2009-04-22
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)
Date modified: