Abstract
This paper investigates the problem of image segmentation using superpixels. We propose two approaches to enhance the discriminative ability of the superpixel’s covariance descriptors. In the first one, we employ the Log-Euclidean distance as the metric on the covariance manifolds, and then use the RBF kernel to measure the similarities between covariance descriptors. The second method is focused on extracting the subspace structure of the set of covariance descriptors by extending a low rank representation algorithm on to the covariance manifolds. Experiments are carried out with the Berkly Segmentation Dataset, and compared with the state-of-the-art segmentation algorithms, both methods are competitive.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. TPAMI 33(5), 898–916 (2011)
Arsigny, V., Fillard, P., Pennec, X., Ayache, N.: Fast and Simple Computations on Tensors with Log-euclidean Metrics, Phd thesis, INRIA (2005)
Cai, J.-F., Candès, E.J., Shen, Z.: A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20(4), 1956–1982 (2010)
Candès, E.J., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? J. ACM (JACM) 58(3), 11 (2011)
Chen, J., Yang, J.: Robust subspace segmentation via low-rank representation. IEEE Trans. Cybern. 44(8), 1432–1445 (2014)
Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24(5), 603–619 (2002)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)
Freixenet, J., Muñoz, X., Raba, D., MartÃ, J., CufÃ, X.: Yet another survey on image segmentation: region and boundary information integration. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part III. LNCS, vol. 2352, pp. 408–422. Springer, Heidelberg (2002)
Fu, Y., Gao, J., Hong, X., Tien, D.: Low rank representation on Riemannian manifold of symmetric positive definite matrices. In: Proceedings of SDM. SIAM (2015)
Ganesh, A., Lin, Z., Wright, J., Wu, L., Chen, M., Ma, Y.: Fast algorithms for recovering a corrupted low-rank matrix. In: 2009 3rd IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), pp. 213–216. IEEE (2009)
Gu, X., Deng, J.D., Purvis, M.K.: Improving superpixel-based image segmentation by incorporating color covariance matrix manifolds. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 4403–4406. IEEE (2014)
Habiboğlu, Y.H., Günay, O., Çetin, A.E.: Covariance matrix-based fire and flame detection method in video. Mach. Vis. Appl. 23(6), 1103–1113 (2012)
Harandi, M.T., Sanderson, C., Wiliem, A., Lovell, B.C.: Kernel analysis over Riemannian manifolds for visual recognition of actions, pedestrians and textures. In: 2012 IEEE Workshop on Applications of Computer Vision (WACV), pp. 433–439. IEEE (2012)
Jayasumana, S., Hartley, R., Salzmann, M., Li, H., Harandi, M.: Kernel methods on Riemannian manifolds with Gaussian RBF kernels. IEEE Trans. Pattern Anal. Mach. Intell. 37(12), 2464–2477 (2015). IEEE
Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM Rev. 51(3), 455–500 (2009)
Li, Z., Wu, X.-M., Chang, S.-F.: Segmentation using superpixels: a bipartite graph partitioning approach. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 789–796. IEEE (2012)
Lin, Z., Chen, M., Ma, Y.: The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices (2010). arXiv preprint arXiv:1009.5055
Liu, G., Lin, Z., Yan, S., Sun, J., Yu, Y., Ma, Y.: Robust recovery of subspace structures by low-rank representation. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 171–184 (2013)
Liu, G., Yan, S.: Latent low-rank representation for subspace segmentation and feature extraction. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 1615–1622. IEEE (2011)
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: ICCV 2001, vol. 2, pp. 416–423 (2001)
Meilă, M.: Comparing clusterings: an axiomatic view. In: ICML 2005, pp. 577–584. ACM (2005)
Unnikrishnan, R., Pantofaru, C., Hebert, M.: Toward objective evaluation of image segmentation algorithms. TPAMI 29(6), 929–944 (2007)
Wang, B., Hu, Y., Gao, J., Sun, Y., Yin, B.: Kernelized low rank representation on grassmann manifolds (2015). arXiv preprint arXiv:1504.01806
Wang, B., Hu, Y., Gao, J., Sun, Y., Yin, B.: Low rank representation on grassmann manifolds: an extrinsic perspective (2015). arXiv preprint arXiv:1504.01807
Wang, X., Li, H., Masnou, S., Chen, L.: Sparse coding and mid-level superpixel-feature for \(\ell \) \(_\text{0 }\)-graph based unsupervised image segmentation. In: Wilson, R., Hancock, E., Bors, A., Smith, W. (eds.) CAIP 2013, Part II. LNCS, vol. 8048, pp. 160–168. Springer, Heidelberg (2013)
Wright, J., Ganesh, A., Rao, S., Peng, Y., Ma, Y.: Robust principal component analysis: exact recovery of corrupted low-rank matrices via convex optimization. In: Advances in Neural Information Processing Systems, pp. 2080–2088 (2009)
Xie, Y., Ho, J., Vemuri, B.: On a nonlinear generalization of sparse coding and dictionary learning. In: Proceedings of the International Conference on Machine Learning, p. 1480. NIH Public Access (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix: Solution of Eq. (4)
Appendix: Solution of Eq. (4)
The solution of Eq. (4) is partly refer to the work of Wang et al. [24], but the distance induced by Frobenius norm is not geodesic. The problem is rephrased as follows.
Find a matrix Z that satisfied,
where, \(\mathcal {X}\) is a 3-order tensor stacking by covariance matrices \((X_i)_{d\times d}\), \(i=1,2,...,n\); \(\Vert \cdot \Vert _F\) is the Frobenius norm; \(\Vert \cdot \Vert _{*}\) is the nuclear norm; \(\lambda \) is the balance parameter; \(\times _3\) means mode-3 multiplication of a tensor and matrix [15].
For the error term E, we have \(\Vert E\Vert _F^2 = \Vert \mathcal {X}-\mathcal {X}_{\times 3}Z\Vert _{F}^2\), and we can rewrite \(\Vert E\Vert _F^2\) as,
where, \(E_i = X_i - \sum _j^Nz_{ij}X_j \), i.e. the i-th slice of E.
Note that for matrix A, it holds \(\Vert A\Vert _{F}^2 = tr(A^TA)\), and \(X_i\) is symmetric, so, the above equation can be expanded as,
Let \(\varDelta \) be a symmetric matrix of size \(N\times N\), whose entries are \(\varDelta _{ij}=\varDelta _{ji}=tr(X_iX_j)\). Because \(X_i\) is a symmetric matrix, \(\varDelta _{ij}\) can be written as \(\varDelta _{ij}=vec(X_i)^Tvec(X_j)\), where \(vec(\cdot )\) is an operator that vectorized a matrix. As a Gram matrix, \(\varDelta \) is positive semidefinite. So, we have,
For \(\varDelta = PP^T\),
Then, the optimization is equivalent to:
Let \(\varDelta \) be a symmetric matrix, whose entries are \(\varDelta _{ij}=\varDelta _{ji}=tr(X_iX_j)\), and \(P = \varDelta ^{\frac{1}{2}}\). First, we transform the above equation into an equivalent formulation
Then by ALM, we have,
where, Y is the Lagrange coefficient, \(\lambda \) and \(\mu \) are scale parameters.
The above problem can be solved by the following two subproblems [17],
and,
Fortunately according to [3], the solutions for the above subproblems have the following close forms,
where, \(\varTheta (\cdot )\) is the singular value thresholding operator [3].
Thus, by iteratively updating J and Z until the converge conditions are satisfied, a solution for Eq. (4) can be found.
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Gu, X., Purvis, M. (2016). Image Segmentation with Superpixel Based Covariance Descriptor. In: Cao, H., Li, J., Wang, R. (eds) Trends and Applications in Knowledge Discovery and Data Mining. PAKDD 2016. Lecture Notes in Computer Science(), vol 9794. Springer, Cham. https://doi.org/10.1007/978-3-319-42996-0_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-42996-0_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-42995-3
Online ISBN: 978-3-319-42996-0
eBook Packages: Computer ScienceComputer Science (R0)