We consider descriptors in polar and log-polar coordinates that produce compact description of the image near interest points. These descriptors may be used to establish one-to-one correspondence between points in two images. Algorithms to compute these descriptors are described and the results of a numerical experiment comparing them with SIFT and SURF descriptors are reported. The numerical experiment suggests that the proposed descriptors are highly efficient for finding conjugate points in two images.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
D. G. Lowe, “Image features from scale-invariant keypoints,” Int. J. Comput. Vis., 60, No. 2, 91–110 (2004).
H. Bay, A. Ess, T. Tuytelaars, and L. V. Gool, “SURF: speeded up robust features,” Comput. Vis. Image Underst. (CVIU), 110, No. 3, 346–359 (2008).
L. A. Torres-Méndez, J. C. Ruiz-Suárez, L. E. Sucar, and G. Gómez, “Translation, rotation, and scale-invariant object recognition,” IEEE Trans. Systems, Man and Cybern., 30, No. 1, 125–130 (2000).
S. Zokai and G. Wolberg, “Image registration using log-polar mappings for recovery of large-scale similarity and projective transformations,” IEEE Trans. Image Process, 14, No. 10, 1422–1434 (2005).
E. Castro and C. Morandi, “Registration of translated and rotated images using finite Fourier transforms,” IEEE Trans. Pattern Anal. Mach. Intell., 9, No. 5, 700–703 (1987).
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated from Prikladnaya Matematika i Informatika, No. 52, 2016, pp. 83–92.
Rights and permissions
About this article
Cite this article
Lukianitsa, A.A. Efficient Local Image Descriptors. Comput Math Model 28, 237–244 (2017). https://doi.org/10.1007/s10598-017-9360-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10598-017-9360-7