Efficient Local Image Descriptors
- Authors: Lukianitsa A.A.1
-
Affiliations:
- Faculty of Computational Mathematics and Cybernetics, Moscow State University
- Issue: Vol 28, No 2 (2017)
- Pages: 237-244
- Section: Article
- URL: https://ogarev-online.ru/1046-283X/article/view/247602
- DOI: https://doi.org/10.1007/s10598-017-9360-7
- ID: 247602
Cite item
Abstract
We consider descriptors in polar and log-polar coordinates that produce compact description of the image near interest points. These descriptors may be used to establish one-to-one correspondence between points in two images. Algorithms to compute these descriptors are described and the results of a numerical experiment comparing them with SIFT and SURF descriptors are reported. The numerical experiment suggests that the proposed descriptors are highly efficient for finding conjugate points in two images.
Keywords
About the authors
A. A. Lukianitsa
Faculty of Computational Mathematics and Cybernetics, Moscow State University
Author for correspondence.
Email: andrei.luk@gmail.com
Russian Federation, Moscow
Supplementary files
