Abstract
The paper presents an image matching method based on heat kernels. The method permits one to single out the most stable features of images at the initial stage using heat kernels on graphs for subsequent comparison. Popular descriptors can be used for this. When using the method, the number of false matches is considerably reduced compared with traditional approaches.
Similar content being viewed by others
REFERENCES
Krig, S., Computer Vision Metrics. Survey, Taxonomy, and Analysis, Berkeley: Apress, 2014.
Ojala, T., Pietikainen, M., and Hardwood, D., A comparative study of texture measures with classification based on feature distributions, Pattern Recognit., 1996, vol. 29, no. 1, pp. 51–59. https://doi.org/10.1016/0031-3203(95)00067-4
Calonder, M., Lepetit, V., Strecha, C., and Fua, P., BRIEF: Binary Robust Independent Elementary Features, in Computer Vision—ECCV 2010, vol. 6314 of Lecture Notes in Computer Science, Daniilidis, K., Maragos, P., and Paragios, N., Eds., Berlin–Heidelberg: Springer, 2010. https://doi.org/10.1007/978-3-642-15561-1_56
Rublee, E., Rabaud, V., Konolige, K., and Bradski, G., ORB: An efficient alternative to SIFT or SURF, 2011 Int. Conf. Comput. Vis. (2011), pp. 2564-2571. https://doi.org/10.1109/ICCV.2011.6126544
Leutenegger, S., Chli, M., and Siegwart, R., BRISK: Binary Robust Invariant Scalable Keypoints, 2011 Int. Conf. Comput. Vis. (2011), pp. 2548–2555. https://doi.org/10.1109/ICCV.2011.6126542
Lowe, D.G., Distinctive image features from scale-invariant keypoints, Int. J. Comput. Vis., 2004, vol. 60, no. 2, pp. 91–110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
Bay, H., Ess, A., Tuytelaars, T., and Van Gool, L., SURF: Speeded Up Robust Features, Comput. Vis. Image Understand., 2008, vol. 110, no. 3, pp. 346–359. https://doi.org/10.1007/11744023_32
Tola, E., Lepetit, V., and Fua, P., DAISY: An efficient dense descriptor applied to wide-baseline stereo, IEEE Trans. Pattern Anal. Mach. Intell., 2010, vol. 32, no. 5, pp. 815–830. https://doi.org/10.1109/TPAMI.2009.77
Dalal, N. and Triggs, B., Histograms of oriented gradients for human detection, Comput. Vis. Pattern Recognit., 2005, vol. 1, pp. 886–893. https://doi.org/10.1109/CVPR.2005.177
Scharstein, D. and Szeliski, R., A taxonomy and evaluation of dense two-frame stereo correspondence algorithms, Int. J. Comput. Vis., 2002, no. 47, pp. 7–42. https://doi.org/10.1023/A:1014573219977
Jun, B. and Kim, D., Robust face detection using local gradient patterns and evidence accumulation, Pattern Recognit., 2012, vol. 45, no. 9, pp. 3304–3316. https://doi.org/10.1016/j.patcog.2012.02.031
Bracewell, R., The Fourier Transform and Its Applications, McGraw-Hill Sci./Eng./Math., 1999.
Ren, X. and Ramanan, D., Histograms of sparse codes for object detection, Conf. Comput. Vis. Pattern Recognit. (2013). https://doi.org/10.1109/CVPR.2013.417
Matas, J., Chum, O., Urba, M., and Pajdla, T., Robust wide baseline stereo from maximally stable extremal regions, Proc. Br. Mach. Vis. Conf. (2002). https://doi.org/10.1016/j.imavis.2004.02.006
Yang, M., Kpalma, K., and Ronsin, J., A survey of shape feature extraction techniques, Pattern Recognit., 2008, pp. 43–90. https://doi.org/10.5772/6237
Szeliski, R., Computer Vision: Algorithms and Applications, Heidelberg: Springer, 2010.
Ufer, N. and Ommer, B., Deep semantic feature matching, 2017 IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) (2017), pp. 5929–5938. https://doi.org/10.1109/CVPR.2017.628
Gao, Q., Wang, F., Xue, N., Yu, J.G., and Xia, G.S., Deep graph matching under quadratic constraint, 2021 IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) (2021), pp. 5067–5074. https://doi.org/10.1109/CVPR46437.2021.00503
Scott, G. and Longuet-Higgins, H., An algorithm for associating the features of two images, Proc. R. Soc., 1991, vol. 244, pp. 21–26. https://doi.org/10.1098/rspb.1991.0045
Zakharov, A.A., Zhiznyakov, A.L., and Titov, V.S., A method for feature matching in images using descriptor structures, Comput. Opt., 2019, vol. 43, no. 5, pp. 811–818. https://doi.org/10.18287/2412-6179-2019-43-5-811-818
Shapiro, L.S. and Brady, J.M., Feature-based correspondence—an eigenvector approach, Image Vis. Comput., 1992, vol. 10, no. 5, pp. 283–288. https://doi.org/10.1016/0262-8856(92)90043-3
Carcassoni, M. and Hancock, E., Spectral correspondence for point pattern matching, Pattern Recognit., 2003, vol. 36, no. 1, pp. 193–204. https://doi.org/10.1016/S0031-3203(02)00054-7
Leordeanu, M. and Hebert, M., A spectral technique for correspondence problems using pairwise constraints, Tenth IEEE Int. Conf. Comput. Vis. 2005, vol. 1. https://doi.org/10.1109/ICCV.2005.20
Cour, T., Srinivasan, P., and Shi, J., Balanced graph matching, Proc. Conf. Neural Inf. Process. Syst. (2006). https://doi.org/10.7551/mitpress/7503.003.0044
Delponte, E., Isgro, F., Odone, F., and Verri, A., SVD-matching using SIFT features, Graphical Models, 2006, vol. 68, no. 5–6, pp. 415–431. https://doi.org/10.1016/j.gmod.2006.07.002
Chung, F.R.K., Spectral Graph Theory, Providence: Am. Math. Soc., 1997.
Zakharov, A.A., Titov, D.V., Zhiznyakov, A.L., and Titov, V.S., Visual attention method based on vertex ranking of graphs by heterogeneous image attributes, Comput. Opt., 2020, vol. 44, no. 3, pp. 427–435. https://doi.org/10.18287/2412-6179-CO-658
Zakharov, A.A., Barinov, A.E., Zhiznyakov, A.L., and Titov, V.S., Object detection in images with a structural descriptor based on graphs, Comput. Opt., 2018, vol. 42, no. 2, pp. 283–290. https://doi.org/10.18287/2412-6179-2018-42-2-283-290
Zakharov, A., Barinov, A., and Zhiznyakov, A., Faces selection in images using the spectral graph theory and constraints, 2017 Int. Conf. Ind. Eng. Appl. Manuf. (2017). https://doi.org/10.1109/ICIEAM.2017.8076407
Zakharov, A., Tuzhilkin, A., and Zhiznyakov, A., Automatic building detection from satellite images using spectral graph theory, Int. Conf. Mech. Eng. Autom. Control Syst. (MEACS) (2015). https://doi.org/10.1109/MEACS.2015.7414937
Bai, X., Wilson, R.C., and Hancock, E.R., Characterising graphs using the heat kernel, Br. Mach. Vis. Conf. (2005), pp. 315–324. https://doi.org/10.5244/C.19.92
Ghawalby, H. and Hancock, E.R., Heat kernel embeddings, differential geometry and graph structure, Axioms, 2015, vol. 4, pp. 275–293. https://doi.org/10.3390/axioms4030275
Funding
This work was financially supported by the Ministry of Science and Higher Education of the Russian Federation, state order no. GB-1187/20 for Vladimir State University.
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated by V. Potapchouck
Rights and permissions
About this article
Cite this article
Zakharov, A.A. An Image Matching Method Using Heat Kernels on Graphs. Autom Remote Control 83, 1538–1543 (2022). https://doi.org/10.1134/S0005117922010006X
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0005117922010006X