Preview

Doklady BGUIR

Advanced search

SECTOR LOCALIZATION, PARAMETERIZATION AND IDENTIFICATION OF REFERENCE POINTS BASED ON CORNER COEFFICIENTS FOR ALIGNING THE OVERLAPPING IMAGES

Abstract

Algorithms of sector localization and parameterization of reference points in the wavelet domain for aligning the overlapping images based on the utility of corner coefficients to describe the contour structure in the vicinity of the reference point are proposed. It is shown that these algorithms compared to the methods of SIFT and SURF provide a reduction in the computational complexity of localization and parameterization of reference points and increase the stability of their descriptors at parallax.

About the Authors

O. J. Al-Furaiji
Белорусский государственный университет информатики и радиоэлектроники
Belarus


V. K. Kanapelka
Белорусский государственный университет информатики и радиоэлектроники
Belarus


V. YU. Tsviatkou
Белорусский государственный университет информатики и радиоэлектроники
Belarus


References

1. Lowe D.G. // International Journal of Computer Vision. 2004, Vol. 60, № 2. P. 91-110.

2. H. Bay, et. al. // Computer Vision and Image Understanding. 2008, Vol. 110, № 3. P. 346-359.

3. Малла С. Вэйвлеты в обработке сигналов. М., 2005.

4. Гонсалес Р., Вудс Р. Цифровая обработка изображений. М., 2005.

5. Fog A. Optimization manuals, 4th, Instruction tables: Lists of instruction latencies, throughputs and micro-operation. Copenhagen University College of Engineering. 2012.

6. Аль-Фурайджи О.Дж., Спичекова Н.В. // Сб. междунар. научн.-техн. семинара. Телекоммуникации: сети и технологи, алгебраическое кодирование и безопасность данных. 2010. С. 51-56.

7. Fischler M.A., Bolles R.C. // Communications of the ACM. 1981., Vol. 24, № 6. - P. 381-395.


Review

For citations:


Al-Furaiji O.J., Kanapelka V.K., Tsviatkou V.Yu. SECTOR LOCALIZATION, PARAMETERIZATION AND IDENTIFICATION OF REFERENCE POINTS BASED ON CORNER COEFFICIENTS FOR ALIGNING THE OVERLAPPING IMAGES. Doklady BGUIR. 2012;(6):122-128. (In Russ.)

Views: 387


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


ISSN 1729-7648 (Print)
ISSN 2708-0382 (Online)