Affiliation:
1. Povolzhskiy State University of Telecommunications and Informatics
Abstract
Superposition of the similarity images is implemented by the methodology with divided estimation of parameters. The offsets along the coordinate axes are estimated in the Cartesian coordinate system. The scale and the rotate are estimated in the log-polar coordinate system. The accurate estimation of parameters of similarity models (offsets, scale and rotate) is achieved by the iteration processing. Optimization of the processing time is achieved by contour comparison instead of the image comparison. The test data for experiment is image with the freight car. The decreasing of the processing time for the modified methodology of “contour comparison” was estimated by comparison with the source methodology of “image comparison”.
Publisher
Bonch-Bruevich State University of Telecommunications
Reference16 articles.
1. Ke Y., Sukthankar R. PCA-SIFT: A more distinctive representation for local image descriptors. Computer Vision and Pattern Recognition. 2004;2:506‒513. DOI:10.1109/CVPR.2004.1315206
2. Bay H., Tuytelaars T., Van Gool L. Surf: Speeded up robust features. Proceedings of the 9th European Conference on Computer Vision, ECCV 2006, 7‒13 May 2006, Graz, Austria. Lecture Notes in Computer Science. vol.3951. Berlin, Heidelberg: Springer; 2006. p.404‒417. DOI:10.1007/11744023_32
3. Sungatullina D., Krilov A. A fast algorithm for contours image superposition, which connected by an isotropic affine transformation. GraphiCon. 2014:92‒95. (in Russ.) URL: https://www.graphicon.ru/html/2014/papers/92-95.pdf [Accessed 11th May 2023]
4. Novikov A.I., Sablina V.A., Goryachev E.O. Contour analysis application for image superimposition. Izvestiya TulGU. Technical Sciences. 2013;9-1:260‒270. (in Russ.)
5. Elesina S.I., Efimov A.I. Selection of criterial functions for combined and enhanced synthetic vision systems. Izvestiya TulGU. Technical Sciences. 2013;99-1:229‒236. (in Russ.)