UDC 004.627
A. E. Moskvitin, PhD (technical sciences), Leading Researcher, RSREU, Ryazan, Russia;
orcid.org/0000-0003-0358-3953, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
D. V. Borisov, Researcher, scientific research institute «Photon», RSREU, Ryazan, Russia;
orcid.org/0009-0002-8877-1979, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
A. V. Solovyev, R&D Engineer, scientific research institute «Photon», RSREU, Ryazan, Russia;
orcid.org/0000-0002-0383-8955, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
S. A. Ryabinin, Technician, scientific research institute «Photon», RSREU, Ryazan, Russia;
orcid.org/0009-0007-7745-8641X, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The paper considers the problem of comparing correlation methods used to estimate offset, scaling and
rotation of color channels of images. The aim of the work is to determine the most efficient correlation method,
which provides maximum accuracy of channel alignment. Three methods are analyzed in the study:
Pearson correlation, cross-correlation and mutual information. For each method, the values of standard
deviation (SD) and percentage error are calculated, which allow to quantify correlation methods. The practical
application of the proposed approaches is possible in computer vision systems, medical imaging and
satellite image processing.
Key words: correlation, image processing, color channels, offset, scaling, rotation, mutual information,
cross-correlation, standard deviation, computer vision