Abstract
A resolution-independent image models the true intensity function underlying a standard image of discrete pixels. Previous work on resolution-independent images demonstrated their efficacy, primarily by employing regularizers that penalize discontinuity. This paper extends the approach by permitting the curvature of resolution-independent images to be regularized. The main theoretical contribution is a generalization of the well-known elastica energy for regularizing curvature. Experiments demonstrate that (i) incorporating curvature improves the quality of resolution-independent images, and (ii) the resulting images compare favorably with another state-of-the-art curvature regularization technique.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Adams, M.D.: An improved content-adaptive mesh-generation method for image representation. In: Proc. ICIP (2010)
Chan, T.F., Kang, S.H., Shen, J.: Euler’s elastica and curvature-based inpainting. SIAM Journal on Applied Mathematics 63(2), 564–592 (2002)
Euler, L.: Methodus inveniendi lineas curvas maximi minimive proprietate gaudentes. Bousquet (1744)
Goldluecke, B., Cremers, D.: Introducing total curvature for image processing. In: Proc. ICCV, pp. 1267–1274 (2011)
Koenderink, J.J., van Doorn, A.J.: Surface shape and curvature scales. Image and Vision Computing 10(8), 557–564 (1992)
MacCormick, J., Fitzgibbon, A.: Curvature regularization for resolution-independent images. Tech. rep., Dickinson College (2013)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proc. ICCV, pp. 416–423 (2001)
Masnou, S., Morel, J.M.: Level lines based disocclusion. In: Proc. ICIP, pp. 259–263 (1998)
Mitiche, A., Ben Ayed, I.: Variational and Level Set Methods in Image Segmentation. Springer (2011)
Mumford, D.: Elastica and computer vision. In: Bajaj, C. (ed.) Algebraic Geometry and Its Applications, pp. 491–506. Springer (1994)
Nocedal, J., Wright, S.J.: Numerical Optimization. Springer (1999)
Osher, S., Fedkiw, R.: Level Set Methods and Dynamic Implicit Surfaces. Springer (2003)
Paul Chew, L.: Constrained delaunay triangulations. Algorithmica 4, 97–108 (1989)
Sarkis, M., Diepold, K.: Content adaptive mesh representation of images using binary space partitions. IEEE Trans. Image Processing 18(5), 1069–1079 (2009)
Schoenemann, T., Kahl, F., Cremers, D.: Curvature regularity for region-based image segmentation and inpainting: A linear programming relaxation. In: Proc. ICCV, pp. 17–23 (2009)
Sethian, J.A.: Level Set Methods and Fast Marching Methods, 2nd edn. Cambridge University Press (1999)
Strandmark, P., Kahl, F.: Curvature regularization for curves and surfaces in a global optimization framework. In: Boykov, Y., Kahl, F., Lempitsky, V., Schmidt, F.R. (eds.) EMMCVPR 2011. LNCS, vol. 6819, pp. 205–218. Springer, Heidelberg (2011)
Vasilescu, M., Terzopoulos, D.: Adaptive meshes and shells: Irregular triangulation, discontinuities, and hierarchical subdivision. In: Proc. CVPR, pp. 829–832 (1992)
Viola, F.: Resolution-independent image models. Ph.D. thesis, University of Cambridge (2011)
Viola, F., Cipolla, R., Fitzgibbon, A.: A unifying resolution-independent formulation for early vision. In: Proc. CVPR (2012)
Ziemer, W.P.: Weakly Differentiable Functions: Sobolev Spaces and Functions of Bounded Variation. Springer (1989)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
MacCormick, J., Fitzgibbon, A. (2013). Curvature Regularization for Resolution-Independent Images. In: Heyden, A., Kahl, F., Olsson, C., Oskarsson, M., Tai, XC. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2013. Lecture Notes in Computer Science, vol 8081. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40395-8_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-40395-8_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40394-1
Online ISBN: 978-3-642-40395-8
eBook Packages: Computer ScienceComputer Science (R0)