UDC 004.932
P. V. Babayan, Ph.D. (in technical sciences.), associate professor, Head of the Department, RSREU named after V.F. Utkin, Ryazan, Russia;
orcid.org/0000-0003-4041-3101, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
E. S. Zhgutova, post-graduate student, RSREU named after V.F. Utkin, Ryazan, Russia;
orcid.org/0000-0003-4498-2694, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The paper considers the problem of estimating the accuracy of image alignment after compensation of geometric transformations. The aim of the work is to develop and provide a general description of an algo rithm for estimating the accuracy of image alignment, in which the accuracy is characterized by a correla tion matrix of geometric transformation parameters. The following types of transformations are considered: Euclidean, similarity, affine, bilinear. Experimental studies are presented, the purpose of which was to show how the choice of reference points in an image affects the accuracy of estimating the parameters of geomet ric transformation and then further alignment of images. For these purposes software has been developed that allows experimental studies for various types of transformations. The results obtained can be taken into account when developing stabilization algorithms or object selection algorithms for mobile image sensors, which will reduce the number of false selections by improving the accuracy of image alignment.
Key words: : geometric transformations, image alignment, transformation estimation, Euclidean trans formations, similarity transformation, affine transformations, bilinear transformations, correlation matrix, image alignment accuracy estimation.