Abstract
Faithful representation of pairwise pixel affinities is crucial for the outcome of spectral segmentation methods. In conventional affinity models only close-range pixels interact, and a variety of subsequent techniques aims at faster propagation of local grouping cues across long-range connections. In this paper we propose a general framework for constructing a full-range affinity matrix. Our affinity matrix consists of a global similarity matrix and an additive proximity matrix. The similarity in appearance, including intensity and texture, is encoded for each pair of image pixels. Despite being full-range, our similarity matrix has a simple decomposition, which exploits an assignment of image pixels to dictionary elements. The additive proximity enforces smoothness to the segmentation by imposing interactions between near-by pixels. Our approach allows us to assess the advantages of using a full-range affinity for various spectral segmentation problems. Within our general framework we develop a few variants of full affinity for experimental validation. The performance we accomplish on composite textured images is excellent, and the results on natural images are promising.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 898–916 (2011)
Cour, T., Benezit, F., Shi, J.: Spectral segmentation with multiscale graph decomposition. In: Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1124–1131. IEEE (2005)
Dahl, A.B., Dahl, V.A.: Dictionary based image segmentation. In: Paulsen, R.R., Pedersen, K.S. (eds.) SCIA 2015. LNCS, vol. 9127, pp. 26–37. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-19665-7_3
Dahl, V.A., Dahl, A.B.: A probabilistic framework for curve evolution. In: Lauze, F., Dong, Y., Dahl, A.B. (eds.) SSVM 2017. LNCS, vol. 10302, pp. 421–432. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-58771-4_34
Golub, G., Van Loan, C.F.: Matrix Computations, p. 642. Johns Hopkins University Press, Baltimore (1996)
Kim, T.H., Lee, K.M., Lee, S.U.: Learning full pairwise affinities for spectral segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1690–1703 (2013)
Li, Z., Wu, X.M., Chang, S.F.: Segmentation using superpixels: a bipartite graph partitioning approach. In: Conference on Computer Vision and Pattern Recognition, pp. 789–796. IEEE (2012)
Lillo, A.D., Motta, G., Storer, J., et al.: Texture classification based on discriminative features extracted in the frequency domain. In: International Conference on Image Processing, vol. 2, pp. II–53. IEEE (2007)
Mairal, J., Bach, F., Ponce, J., Sapiro, G., Zisserman, A.: Discriminative learned dictionaries for local image analysis. In: Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2008)
Malik, J., Belongie, S., Leung, T., Shi, J.: Contour and texture analysis for image segmentation. Int. J. Comput. Vis. 43(1), 7–27 (2001)
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: International Conference on Computer Vision, vol. 2, pp. 416–423. IEEE (2001)
Randen, T., Husoy, J.H.: Filtering for texture classification: a comparative study. IEEE Trans. Pattern Anal. Mach. Intell. 21(4), 291–310 (1999)
Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 888–905 (2000)
Skretting, K., Engan, K.: Energy minimization by \(\alpha \)-erosion for supervised texture segmentation. In: Campilho, A., Kamel, M. (eds.) ICIAR 2014. LNCS, vol. 8814, pp. 207–214. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-11758-4_23
Von Luxburg, U.: A tutorial on spectral clustering. Stat. Comput. 17(4), 395–416 (2007)
Wang, X., Li, H., Bichot, C.E., Masnou, S., Chen, L.: A graph-cut approach to image segmentation using an affinity graph based on \(\ell _0\)-sparse representation of features. In: International Conference on Image Processing, pp. 4019–4023. IEEE (2013)
Wang, X., Tang, Y., Masnou, S., Chen, L.: A global/local affinity graph for image segmentation. IEEE Trans. Image Process. 24(4), 1399–1411 (2015)
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
Dahl, V.A., Dahl, A.B. (2019). Global Similarity with Additive Smoothness for Spectral Segmentation. In: Lellmann, J., Burger, M., Modersitzki, J. (eds) Scale Space and Variational Methods in Computer Vision. SSVM 2019. Lecture Notes in Computer Science(), vol 11603. Springer, Cham. https://doi.org/10.1007/978-3-030-22368-7_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-22368-7_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-22367-0
Online ISBN: 978-3-030-22368-7
eBook Packages: Computer ScienceComputer Science (R0)