UDC 004.932.4; 621.384.3; 528.029.67
IMAGE FUSION BY THE METHOD OF PRINCIPAL COMPONENT ANALYSIS WITH ADAPTATION TO NOISE POWER
A. S. Sychev, post-graduate student, RSREU, Ryazan, Russia;
orcid.org/0000-0003-4983-1545, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
I. S. Kholopov, Ph.D. (Tech.), Dean of radio engineering and telecommunications faculty, RSREU, Ryazan, Russia;
orcid.org/0000-0001-5220-0811, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
We consider the problem of image fusion by multispectral vision system in which quality criterion is peak signal-to-noise ratio. The aim of the work is to develop a fusion algorithm that allows creating an image that is comfortable for a subjective observer, even if the image in one of the channels of multispectral vision system contains powerful high-frequency noise component. Experimental results show that the algorithm developed provides the gain in a peak signal-to-noise ratio by 3.4 and 4.6 times compared with the known fusion methods based on principal component analysis and arithmetic mean calculation respectively.
Key words: multispectral vision system, image fusion, principal component analysis, signal to noise ratio, modified gray level variance, image quality measures.