cvpr cvpr2013 cvpr2013-240 cvpr2013-240-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Samuele Salti, Alessandro Lanza, Luigi Di_Stefano
Abstract: The paper conjectures and demonstrates that repeatable keypoints based on salient symmetries at different scales can be detected by a novel analysis grounded on the wave equation rather than the heat equation underlying traditional Gaussian scale–space theory. While the image structures found by most state-of-the-art detectors, such as blobs and corners, occur typically on planar highly textured surfaces, salient symmetries are widespread in diverse kinds of images, including those related to untextured objects, which are hardly dealt with by current feature-based recognition pipelines. We provide experimental results on standard datasets and also contribute with a new dataset focused on untextured objects. Based on the positive experimental results, we hope to foster further research on the promising topic ofscale invariant analysis through the wave equation.
[1] H. Aanæs,A. L. Dahl, and K. Steenstrup Pedersen. Interesting interest points. Int. J. Comput. Vision, 97(1): 18–35, mar 2012. 5, 6, 8
[2] H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool. Speededup robust features (SURF). Comput. Vis. Image Underst., 110(3):346–359, jun 2008. 5
[3] R. H. Chan, A. Lanza, S. Morigi, and F. Sgallari. An adaptive strategy for the restoration of textured images using fractional order regularization. Numerical Mathematics: Theory, Methods and Applications, 6(1):276–296, jan 2013. 1
[4] R. Cucchiara, L. Di Stefano, and M. Piccardi. Detection of circular objects by wave propagation on a mesh-connected computer. Journal of Parallel and Distributed Computing, 31(1):77–87, 1995. 1, 8
[5] B. Engquist and A. Majda. Absorbing boundary conditions for the numerical simulation of waves. Mathematics of Computation, 31(139):629–651, jul 1977. 2
[6] K. Hanahara and M. Hiyane. A circle-detection algorithm simulating wave propagation. Mach. Vision Appl., 4(2):97– 111, mar 1991. 1, 3
[7] D. Hauagge and N. Snavely. Image matching using local symmetry features. In Proc. IEEE Conf. Computer Vision Pattern Recognition, pages 206–213, 2012. 2
[8] J. Koenderink. The structure of images. Biological Cybernetics, 50(5):363–370, 1984. 1
[9] T. Lindeberg. Scale-Space Theory in Computer Vision. Kluwer Academic Publishers, Norwell, MA, USA, 1994. 1
[10] D. G. Lowe. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision, 60(2):91–1 10, nov 2004. 1, 5
[11] G. Loy and A. Zelinsky. Fast radial symmetry for detecting points of interest. IEEE Trans. Pattern Anal. Mach. Intell., 25(8):959–973, aug 2003. 2
[12] M. Lysaker, A. Lundervold, and X. Tai. Noise removal using fourth-order partial differential equations with applications to medical magnetic resonance images in space and time. IEEE Trans. Img. Proc., 12(12):1579–1590, dec 2003. 1
[13] J. Matas, O. Chum, M. Urban, and T. Pajdla. Robust wide baseline stereo from maximally stable extremal regions. In Proc. British Machine Vision Conference, volume 1 of BMVC’02, pages 384–393, 2002. 5
[14] K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir, and L. V. Gool. A comparison of affine region detectors. Int. J. Comput. Vision, 65(1-2):43–72, nov 2005. 5, 6, 8
[15] S. Osher and L. I. Rudin. Feature-oriented image enhancement using shock filters. SIAM J. Numer. Anal. , 27(4):919– 940, aug 1990. 1
[16] P. Perona and J. Malik. Scale-space and edge detection using anisotropic diffusion. IEEE Trans. Pattern Anal. Mach. Intell., 12(7):629–639, jul 1990. 1
[17] V. Ratner and Y. Y. Zeevi. Denoising-enhancing images on elastic manifolds. Trans. Img. Proc., 20(8):2099–2109, aug 2011. 1
[18] D. Reisfeld, H. Wolfson, and Y. Yeshurun. Context-free attentional operators: the generalized symmetry transform. Int. J. Comput. Vision, 14(2): 119–130, mar 1995. 2
[19] G. L. Scott, S. C. Turner, and A. Zisserman. Using a mixed
[20]
[21]
[22]
[23]
[24] wave/diffusion process to elicit the symmetry set. Image Vision Comput., 7(1):63–70, feb 1989. 1, 3 N. Sochen and Y. Y. Zeevi. Images as manifolds embedded in spatial-feature non-euclidean space. Technical Report CCIT260, Israel Inst. Technol, Haifa, Haifa, Israel, 1998. 8 H. Tek and B. B. Kimia. Symmetry maps of free-form curve segments via wave propagation. Int. J. Comput. Vision, 54(13):35–81, aug 2003. 1, 3 T. Tuytelaars and L. Van Gool. Matching widely separated views based on affine invariant regions. Int. J. Comput. Vision, 59(1):61–85, aug 2004. 5 M. Van Walstijn and K. Kowalczyk. On the numerical solution of the 2D wave equation with compact FDTD schemes. In Proc. Int. Conf. Digital Audio Effects (DAFX08), pages 205–212, 2008. 3 A. P. Witkin. Scale-space filtering. In Proc. Eighth Int. Joint Conf. on Artificial Intelligence, volume 2 of IJCAI’83, pages 1019–1022, 1983. 1 222999000533