Abstract
Many segmentation algorithms describe images in terms of a hierarchy of regions. Although such hierarchies can produce state of the art segmentations and have many applications, they often contain more data than is required for an efficient description. This paper shows Laplacian graph energy is a generic measure that can be used to identify semantic structures within hierarchies, independently of the algorithm that produces them. Quantitative experimental validation using hierarchies from two state of art algorithms show we can reduce the number of levels and regions in a hierarchy by an order of magnitude with little or no loss in performance when compared against human produced ground truth. We provide a tracking application that illustrates the value of reduced hierarchies.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Ahuja, N.: A transform for multiscale image segmentation by integrated edge and region detection. TPAMI 18(12), 1211–1235 (1996)
Ahuja, N., Todorovic, S.: Connected segmentation tree - a joint representation of region layout and hierarchy. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (June 2008)
Arbeláez, P., Maire, M., Fowlkes, C., Malik, J.: From contours to regions: An empitical evaluation. In: Computer Vision and Pattern Recognition (2009)
Bangham, J.A., Harvey, R.W., Ling, P.D., Aldridge, R.V.: Morphological scale-space preserving transforms in many dimensions. Journal of Electronic Imaging 5, 283–299 (1996)
Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. TPAMI 24(5), 603–614 (2002)
Cour, T., Benezit, F., Shi, J.: Spectral segmentation with multiscale graph decomposition. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 2, pp. 1124–1131 (June 2005)
Day, J., So, W.: Singular value inequality and graph energy. Electronic Journal of Linear Algebra 16, 291–299 (2007)
Escolano, F., Hancock, E.R., Lozano, M.A.: Polytopal graph complexity, matrix permanentsm, and embedding. In: da Vitoria Lobo, N., Kasparis, T., Roli, F., Kwok, J.T., Georgiopoulos, M., Anagnostopoulos, G.C., Loog, M. (eds.) S+SSPR 2008. LNCS, vol. 5342, pp. 237–246. Springer, Heidelberg (2008)
Fisher, D.: Iterative optimization and simplification of hierarchical clusterings. J. Artif. Int. Res. 4(1), 147–179 (1996)
Gutman, I., Zhou, B.: Laplacian energy of a graph. Linear Algebra and its applications 414, 29–37 (2006)
Kokkinos, I., Yuille, A.: Hop: Hierarchical object parsing. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 802–809 (June 2009)
Liu, J., Yang, Y.: Multiresolution color image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 16, 689–700 (1994)
Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proceedings of the 7th International Joint Conference on Artificial Intelligence (IJCAI 1981), pp. 674–679 (April 1981)
Martin, D., Fowlkes, C., Malik, K.: Learning to detect natural image boundaries using local brightness, color and texture cues. TPAMI 26(5), 530–549 (2004)
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. 8th Int’l Conf. Computer Vision., vol. 2, pp. 416–423 (2001)
Matas, J., Chum, O., Martin, U., Pajdla, T.: Robust wide basline stereo from maximally stable extremal regions. In: BMVC, pp. 384–393 (2002)
Maire, M.: Arbeláez, P., Fowlkes, C., Malik, J.: Using contours to detect and localize juncations in natural images. In: CVPR (2008)
Paris, S., Durand, F.: A topological approach to hierarchical segmentation using mean shift. In: CVPR, pp. 1–8. IEEE Computer Society Press, Los Alamitos (2007)
Ren, X.: Multi-scale improves boundary detection in natural images. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 533–545. Springer, Heidelberg (2008)
Robles-Kelly, A., Hancock, E.R.: A riemannian approach to graph embedding. Pattern Recognition 40, 1042–1056 (2007)
Shi, J., Malik, J.: Normalized cuts and image segmentation. TPAMI, 888–905 (2000)
Shokoufandeh, A., Dickinson, S.J., Siddiqi, K., Zucker, S.W.: Indexing using a spectral encoding of topological structure. In: International Conference on Pattern Recognition, pp. 491–497 (1999)
Tu, P., Saxena, T., Hartley, R.: Recognizing objects using color-annotated adjacency graphs. In: Shape, Contour and Grouping in Computer Vision, pp. 246–263 (1999)
White, D., Wilson, R.: Mixing spectral representations of graphs. In: International Conference on Pattern Recognition (2006)
Worthington, P., Hancock, E.: Region-based object recognition using shape-from-shading. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 455–471. Springer, Heidelberg (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Song, YZ., Arbelaez, P., Hall, P., Li, C., Balikai, A. (2010). Finding Semantic Structures in Image Hierarchies Using Laplacian Graph Energy. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6314. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15561-1_50
Download citation
DOI: https://doi.org/10.1007/978-3-642-15561-1_50
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15560-4
Online ISBN: 978-3-642-15561-1
eBook Packages: Computer ScienceComputer Science (R0)