Abstract
We propose a general framework to encode various grouping cues for natural image segmentation. We extend the classical Gibbs energy of an MRF to three terms: likelihood energy, coherence energy and separating energy. We encode generative cues in the likelihood and coherence energy to ensure the goodness and feasibility of segmentation, and embed discriminative cues in the separating energy to encourage assigning two pixels with strong separability with different labels. We use a self-validated process to iteratively minimize the global Gibbs energy. Our approach is able to automatically determine the number of segments, and produce a natural hierarchy of coarse-to-fine segmentation. Experiments show that our approach works well for various segmentation problems, and outperforms existing methods in terms of robustness to noise and preservation of soft edges.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Feng, W., Liu, Z.Q.: Region-level image authentication using Bayesian structural content abstraction. IEEE Trans. Image Processing 17(12), 2413–2424 (2008)
Feng, W., Xie, L., Zeng, J., Liu, Z.Q.: Audio-visual human recognition using semi-supervised spectral learning and hidden Markov models. Journal of Visual Languages and Computing 20(3), 188–195 (2009)
Martin, D., Fowlkes, C., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proc. of ICCV 2001, vol. 2, pp. 416–423 (2001)
Sharon, E., Brandt, A., Basri, R.: Fast multiscale image segmentation. In: Proc. of CVPR 2000, vol. 1, pp. 70–77 (2000)
Yu, S.X.: Segmentation using multiscale cues. In: Proc. of CVPR 2004, vol. 1, pp. 247–254 (2004)
Benezit, F., Cour, T., Shi, J.: Spectral segmentation with multiscale graph decomposition. In: Proc. of CVPR 2005, vol. 2, pp. 1124–1131 (2005)
Malik, J., Belongie, S., Leung, T., Shi, J.: Contour and texture analysis for image segmentation. Intl. Journal of Computer Vision 43(1), 7–27 (2001)
Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans. Pattern Anal. Machine Intell. 26(5), 530–549 (2004)
Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Machine Intell. 22(8), 888–905 (2000)
Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts? IEEE Trans. Pattern Anal. Machine Intell. 26(2), 147–159 (2004)
Li, S.Z.: Markov Random Field Modeling in Computer Vision. Springer, Heidelberg (1995)
Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary & region segmentation of objects in n-d images. In: Proc. of ICCV 2001, pp. 105–112 (2001)
Feng, W., Liu, Z.Q.: Self-validated and spatially coherent clustering with net-structured MRF and graph cuts. In: Proc. of ICPR 2006, vol. 4, pp. 37–40 (2006)
Grady, L., Schwartz, E.: Isoperimetric graph partition for image segmentation. IEEE Trans. Pattern Anal. Machine Intell. 28(3), 469–475 (2006)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Intl. Journal of Computer Vision 59(2), 167–181 (2004)
Tu, Z., Zhu, S.C.: Image segmentation by data-driven Markov Chain Monte Carlo. IEEE Trans. Pattern Anal. Machine Intell. 24(5), 657–673 (2002)
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
Feng, W., Xie, L., Liu, ZQ. (2010). Multicue Graph Mincut for Image Segmentation. In: Zha, H., Taniguchi, Ri., Maybank, S. (eds) Computer Vision – ACCV 2009. ACCV 2009. Lecture Notes in Computer Science, vol 5995. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12304-7_67
Download citation
DOI: https://doi.org/10.1007/978-3-642-12304-7_67
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12303-0
Online ISBN: 978-3-642-12304-7
eBook Packages: Computer ScienceComputer Science (R0)