Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/5993
Title: Instance detection by keypoint matching beyond the nearest neighbor
Authors: Uzyıldırım, Furkan Eren
Özuysal, Mustafa
Uzyıldırım, Furkan Eren
Özuysal, Mustafa
Izmir Institute of Technology. Computer Engineering
Keywords: Computer vision
Keypoint matching
Object detection
Issue Date: 1-Nov-2016
Publisher: Springer Verlag
Source: Uzyıldırım, F. E., and Özuysal, M. (2016). Instance detection by keypoint matching beyond the nearest neighbor. Signal, Image and Video Processing, 10(8), 1527-1534. doi:10.1007/s11760-016-0966-6
Abstract: The binary descriptors are the representation of choice for real-time keypoint matching. However, they suffer from reduced matching rates due to their discrete nature. We propose an approach that can augment their performance by searching in the top K near neighbor matches instead of just the single nearest neighbor one. To pick the correct match out of the K near neighbors, we exploit statistics of descriptor variations collected for each keypoint in an off-line training phase. This is a similar approach to those that learn a patch specific keypoint representation. Unlike these approaches, we only use a keypoint specific score to rank the list of K near neighbors. Since this list can be efficiently computed with approximate nearest neighbor algorithms, our approach scales well to large descriptor sets.
URI: http://doi.org/10.1007/s11760-016-0966-6
http://hdl.handle.net/11147/5993
ISSN: 1863-1703
1863-1711
Appears in Collections:Computer Engineering / Bilgisayar Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Files in This Item:
File Description SizeFormat 
5993.pdfMakale834.47 kBAdobe PDFThumbnail
View/Open
Show full item record

CORE Recommender

SCOPUSTM   
Citations

4
checked on Sep 18, 2021

WEB OF SCIENCETM
Citations

4
checked on Sep 18, 2021

Page view(s)

52
checked on Sep 20, 2021

Download(s)

28
checked on Sep 20, 2021

Google ScholarTM

Check

Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.