Abstract
Current image segmentation involves strongly non-uniform, anisotropic and asymmetric measures of path length, which challenges available algorithms. In order to meet these challenges, this paper applies the Finsler metric to the geodesic method based on heat diffusion. This metric is non-Riemannian, anisotropic and asymmetric, which helps the heat to flow more on the features of interest. Experiments demonstrate the feasibility of the proposed method. The experimental results show that our algorithm is of strong robustness and effectiveness. The proposed method can be applied to contour detection and tubular structure segmentation in images, such as vessel segmentation in medical images and road extraction in satellite images and so on.
Supported by the National Science Foundation of China (grant 61625305).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akagi, G., Ishige, K., Sato, R.: The cauchy problem for the finsler heat equation. arXiv preprint arXiv:1710.00456 (2017)
Arbeláez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 898–916 (2011)
Astola, L., Florack, L.: Finsler geometry on higher order tensor fields and applications to high angular resolution diffusion imaging. Int. J. Comput. Vis. 92(3), 325–336 (2011)
Belyaev, A.G., Fayolle, P.A.: On variational and PDE-based distance function approximations. In: Computer Graphics Forum, vol. 34, pp. 104–118. Wiley (2015)
Benmansour, F., Cohen, L.D.: Tubular structure segmentation based on minimal path method and anisotropic enhancement. Int. J. Comput. Vis. 92(2), 192–210 (2011)
Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. Int. J. Comput. Vis. 22(1), 61–79 (1997)
Chen, D., Cohen, L.D.: Fast asymmetric fronts propagation for image segmentation. J. Math. Imaging Vis. 60, 1–18 (2017)
Chen, D., Mirebeau, J.M., Cohen, L.D.: Global minimum for a finsler elastica minimal path approach. Int. J. Comput. Vis. 122(3), 458–483 (2017)
Chern, S.S.: Finsler geometry is just riemannian geometry without the quadratic equation. Not. Am. Math. Soc. 43(9), 959–963 (1996)
Crane, K., Weischedel, C., Wardetzky, M.: Geodesics in heat: a new approach to computing distance based on heat flow. ACM Trans. Graph. (TOG) 32(5), 152 (2013)
Fehrenbach, J., Mirebeau, J.M.: Sparse non-negative stencils for anisotropic diffusion. J. Math. Imaging Vis. 49(1), 123–147 (2014)
Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale vessel enhancement filtering. In: Wells, W.M., Colchester, A., Delp, S. (eds.) MICCAI 1998. LNCS, vol. 1496, pp. 130–137. Springer, Heidelberg (1998). https://doi.org/10.1007/BFb0056195
Hysing, S.R., Turek, S.: The Eikonal equation: numerical efficiency vs. algorithmic complexity on quadrilateral grids. In: Proceedings of Algoritmy, vol. 22 (2005)
Lin, B., Yang, J., He, X., Ye, J.: Geodesic distance function learning via heat flow on vector fields. In: International Conference on Machine Learning, pp. 145–153 (2014)
Melonakos, J., Pichon, E., Angenent, S., Tannenbaum, A.: Finsler active contours. IEEE Trans. Pattern Anal. Mach. Intell. 30(3), 412–423 (2008)
Mirebeau, J.M.: Efficient fast marching with finsler metrics. Numer. Math. 126(3), 515–557 (2014)
Mirebeau, J.M.: Anisotropic fast-marching on cartesian grids using Voronoi’s first reduction of quadratic forms (2017)
Ohta, S.I., Sturm, K.T.: Heat flow on Finsler manifolds. Commun. Pure Appl. Math. 62(10), 1386–1433 (2009)
Peyré, G., Péchaud, M., Keriven, R., Cohen, L.D., et al.: Geodesic methods in computer vision and graphics. Found. Trends® Comput. Graph. Vis. 5(3–4), 197–397 (2010)
Sethian, J.A.: A fast marching level set method for monotonically advancing fronts. Proc. Nat. Acad. Sci. U.S.A. 93(4), 1591–1595 (1996)
Solomon, J., et al.: Convolutional wasserstein distances: efficient optimal transportation on geometric domains. ACM Trans. Graph. (TOG) 34(4), 66 (2015)
Varadhan, S.R.S.: On the behavior of the fundamental solution of the heat equation with variable coefficients. Commun. Pure Appl. Math. 20(2), 431–455 (1967)
Weickert, J.: Coherence-Enhancing Diffusion Filtering. Kluwer Academic Publishers (1999)
Yang, F., Cohen, L.D.: Geodesic distance and curves through isotropic and anisotropic heat equations on images and surfaces. J. Math. Imaging Vis. 55(2), 210–228 (2016)
Yang, F., Cohen, L.D.: Tubular structure segmentation based on heat diffusion. In: Lauze, F., Dong, Y., Dahl, A.B. (eds.) SSVM 2017. LNCS, vol. 10302, pp. 54–65. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-58771-4_5
Zach, C., Shan, L., Niethammer, M.: Globally optimal finsler active contours. In: Denzler, J., Notni, G., Süße, H. (eds.) DAGM 2009. LNCS, vol. 5748, pp. 552–561. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-03798-6_56
Zhao, H.: A fast sweeping method for Eikonal equations. Math. Comput. 74(250), 603–627 (2005)
Zou, Q., Zhang, J., Deng, B., Zhao, J.: Iso-level tool path planning for free-form surfaces. Comput. Aided Des. 53, 117–125 (2014)
Acknowledgements
The authors would like to thank Dr. Jean-Marie Mirebeau for his insightful suggestions on the numerical solutions to asymmetric heat diffusion. The authors would also like to thank Dr. Xin Su for his useful comments that allowed us to improve this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, F., Chai, L., Chen, D., Cohen, L. (2019). Geodesic via Asymmetric Heat Diffusion Based on Finsler Metric. In: Jawahar, C., Li, H., Mori, G., Schindler, K. (eds) Computer Vision – ACCV 2018. ACCV 2018. Lecture Notes in Computer Science(), vol 11365. Springer, Cham. https://doi.org/10.1007/978-3-030-20873-8_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-20873-8_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20872-1
Online ISBN: 978-3-030-20873-8
eBook Packages: Computer ScienceComputer Science (R0)