Abstract
This paper aims to explore frequency behavior of isotropic (regular SIFT) and anisotropic (Bi-SIFT and Tri-SIFT) versions of the scale-space keypoint detection algorithm SIFT. We introduced a new smoothing function Trilateral filter that can be used in formation of a scale-space as an alternative to the Gaussian scale-space. The number of matching pixels, warping error, and scatteredness are employed in comparison. We made the comparison out of face dataset and object dataset for scale, orientation, and view-angle transformations as well as lighting and compression variations. The comparison results show that anisotropic smoothing detects more keypoints than isotropic one. The Tri-SIFT is more robust to variation in viewpoint angle.
Similar content being viewed by others
References
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Lindeberg, T.: Scale-space theory: a basic tool for analysing structures at different scales. J. Appl. Stat. 21(2), 225–270 (1994)
Koenderink, J.J.: The structure of images. Biol. Cybern. 50(5), 363–370 (1984)
Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: International Conference on Computer Vision, Bombay (1998)
Mikolajczyk, K.: Detection of local features invariant to affine transformations. Ph.D. thesis, Institut National Polytechnique de Grenoble, France (2002)
Wu, J., Cui, Z., Sheng, V.S., Zhao, P., Su, D., Gong, S.: A comparative study of SIFT and its variants. Meas. Sci. Rev. 13(3), 122–131 (2013)
Ke, Y., Sukthankar, R.: PCA-SIFT: a more distinctive representation for local image descriptors. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2004)
Mortensen, E.N., Deng, H., Shapiro, L.: A SIFT descriptor with global context. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05) (2005)
Abdel-Hakim, A.E., Farag, A.A.: CSIFT: A SIFT descriptor with color invariant characteristics. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06) (2006)
Morel, J.M., Yu, G.: ASIFT: a new framework for fully affine invariant image comparison. SIAM J. Imaging Sci. 2(2), 438–469 (2009)
Skoch, W., Gauch, J.: The effects of anisotropic Gaussian diffusion in scale invariant feature detection. In: IEEE International Conference on Signal and Image Processing Applications (ICSIPA2011), Kuala Lumpur (2011)
Wang, F.: Adapted anisotropic Gaussian SIFT matching strategy for SAR registration. Geosci. Remote Sens. Lett. 12(1), 160–164 (2015)
Alcantarilla, P.F., Davison, A.B., Andrew, J.: KAZE features. In: In European Conference on Computer Vision (ECCV), Fiorenze, Italy (2012)
Wang, S., Fu, H.Y.K.: BFSIFT: a novel method to find feature matches for SAR image registration. Geosci. Remote Sens. Lett. 9(4), 649–653 (2012)
Huang, M., Mu, Z., Zeng, H., Huang, H.: A novel approach for interest point detection via Laplacian-of-bilateral filter. J. Sens. 2015, 9 (2015)
Databases for Face Detection and Pose Estimation. http://robotics.csie.ncku.edu.tw/Databases/FaceDetect_PoseEstimate.htm#Our_Database_
Chen, J.C., Lien, J.J.J.: A view-based statistical system for multi-view face detection and pose estimation. Image Vis. Comput. 27(9), 1252–1271 (2009)
Affine Covariant Features. http://www.robots.ox.ac.uk/~vgg/research/affine/
Mikolajczyk, T.T.K., Schmid, A.Z.C., Matas, F.S.J., Kadir, T., Gool, L.V.: A comparison of affine region detectors. Int. J. Comput. Vis. 65(1), 43–72 (2005)
http://caitlinsg324mediablog.blogspot.com/2012_12_01_archive.html
https://c1.staticflickr.com/5/4001/4648662998_5ef1a56fa3_z.jpg
http://www.fun-lover.com/graphic-shop/Textures/images/RocksStone/rkt-045.jpg
Author information
Authors and Affiliations
Corresponding author
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Şekeroğlu, K., Soysal, Ö.M. Comparison of SIFT, Bi-SIFT, and Tri-SIFT and their frequency spectrum analysis. Machine Vision and Applications 28, 875–902 (2017). https://doi.org/10.1007/s00138-017-0868-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-017-0868-9