UDC 004.932.2
ANALYSIS OF IMAGE KEY POINT DETECTION, DESCRIPTION AND MATCHING METHODS
A. A. Denisov, post-graduate student, RSREU, Ryazan, Russia;
orcid.org/0009-0006-6765-5054, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
A. I. Novikov, Dr. Sc.(Tech.), full professor, RSREU, Ryazan, Russia;
orcid.org/0000-0002-8166-8234, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The aim of the work is to describe and conduct comparative tests of known detecting and describing image key points methods and algorithms, as well as to establish pairwise correspondence between key points of two images. The objective of the work is to identify the strengths and weaknesses of each of the algorithms. The following algorithms for detecting and describing keypoints were compared in the experiments: SIFT, SURF, FAST/FREAK, BRISK, KAZE and ORB. The comparison of keypoint detectors was carried out according to the criteria of performance and the number of keypoints found. The descriptors were compared in terms of accuracy to establish a correspondence between key points of two images and computational time for key points describing and matching them.
Key words: : keypoint, descriptor, detector, SIFT, SURF, FAST, FREAK, BRISK, KAZE, ORB ORB.