Abstract
Shape priors has greatly enhanced low-level driven image segmentations, however existing graph cut based segmentation methods still restrict to pre-aligned shape priors. The major contribution of this paper is to incorporate transformation-invariant shape priors into the graph cut algorithm for automatic image segmentations. The expectation of shape transformation and image knowledge are encoded into energy functions that is optimized in a MRF maximum likelihood framework using the expectation-maximization. The iteratively updated expectation process improves the segmentation robustness. In turn, the maximum likelihood segmentation is realized integrally by casting the lower-bound of energy function in a graph structure that can be effectively optimized by graph-cuts algorithm in order to achieve a global solution and also increase the accuracy of the probabilities measurement. Finally, experimental results demonstrate the potentials of our method under conditions of noises, clutters, and incomplete occlusions.
P. Tang—This work was supported by the National Natural Science Foundation of China (61134002) and Fundamental Research Funds for the Central Universities (2682014CX027).
This is a preview of subscription content, log in via an institution to check access.
References
Boykov, Y., Funka-Lea, G.: Graph cuts and efficient n-d image segmentation. IJCV 70(2), 109–131 (2006)
Chan, T., Zhu, W.: Level set based shape prior segmentation. In: Proceedings of the IEEE CVPR, vol. 2, pp. 1164–1170, San Diego, CA (2005)
Charpiat, G., Faugeras, O., Keriven, R.: Shape statistics for image segmentation with prior. In: Proceedings of the IEEE CVPR, pp. 1–6, Minneapolis (2007)
Cremers, D.: Dynamical statistical shape priors for level set-based tracking. IEEE Trans. PAMI 28(8), 1262–1273 (2006)
Dambreville, S., Rathi, Y., Tannenbaum, A.: Shape-based approach to robust image segmentation using kernel PCA. In: Proceedings of the IEEE CVPR, vol. 1, pp. 977–984. IEEE Press, New York City (2006)
Doretto, G., Chiuso, A., Wu, Y.N., Soatto, S.: Dynamic textures. IJCV 51(2), 91–109 (2003)
El-Zehiry, N., Xu, S., Sahoo, P., Elmaghraby, A.: Graph cut optimization for the Mumford-Shah model. In: Proceedings of the 7th IASTED International Conference on Visualization Imaging, and Image Processing, pp. 182–187, Palma de Mallorca, Spain (2007)
Freedman, D., Zhang, T.: Interactive graph cut based segmentation with shape priors. In: Proceedings of the IEEE CVPR, vol. 1, pp. 755–761, San Diego, CA (2005)
Hadfield, J.D., et al.: MCMC methods for multi-response generalized linear mixed models: the MCMCglmm R package. J. Stat. Softw. 33(2), 1–22 (2010)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE CVPR, pp. 3431–3440 (2015)
Malcolm, J., Rathi, Y., Tannenbaum, A.: Graph cut segmentation with nonlinear shape priors. Proc. IEEE ICIP 4, 365–368 (2007)
Price, B.L., Morse, B., Cohen, S.: Geodesic graph cut for interactive image segmentation. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3161–3168. IEEE (2010)
Shen, W., Wang, X., Wang, Y., Bai, X., Zhang, Z.: Deepcontour: a deep convolutional feature learned by positive-sharing loss for contour detection. In: Proceedings of the IEEE CVPR, pp. 3982–3991 (2015)
Slabaugh, G., Unal, G.: Graph cuts segmentation using an elliptical shape prior. In: Proceedings of IEEE ICIP, pp. 1222–1225 (2005)
Vicente, S., Kolmogorov, V., Rother, C.: Graph cut based image segmentation with connectivity priors. In: Proceedings of the IEEE CVPR (2008)
Ning, X., Bansal, R., Ahuja, N.: Object segmentation using graph cuts based active contours. Proc. IEEE CVPR 2, 46–53 (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Science+Business Media Singapore
About this paper
Cite this paper
Tang, P., Jin, W. (2016). Automatic Image Semantic Segmentation by MRF with Transformation-Invariant Shape Priors. In: Zhang, L., Song, X., Wu, Y. (eds) Theory, Methodology, Tools and Applications for Modeling and Simulation of Complex Systems. AsiaSim SCS AutumnSim 2016 2016. Communications in Computer and Information Science, vol 643. Springer, Singapore. https://doi.org/10.1007/978-981-10-2663-8_23
Download citation
DOI: https://doi.org/10.1007/978-981-10-2663-8_23
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-2662-1
Online ISBN: 978-981-10-2663-8
eBook Packages: Computer ScienceComputer Science (R0)