Abstract
In this paper, we present a novel nonparametric active region model for image segmentation. This model partitions an image by maximizing the similarity between the image and a label image, which is generated by setting different constants as the intensities of partitioned subregions. The intensities of these two images can not be compared directly as they are of different modalities. In this work we use Rényi’s statistical dependence measure, maximum cross correlation, as a criterion to measure their similarity. By using this measure, the proposed model deals directly with independent samples and does not need to estimate the continuous joint probability density function. Moreover, the computation is further simplified by using the theory of reproducing kernel Hilbert spaces. Experimental results based on medical and synthetic images are provided to demonstrate the effectiveness of the proposed method.
Similar content being viewed by others
References
Mumford, D., Shah, J.: Optimal approximation by piecewise smooth functions and associated variational problems. Commun. Pure Appl. Math. 42, 577–685 (1989)
Chan, T., Vese, L.: Active contours without edges. IEEE Trans. Image Process. 10(2), 266–277 (2001)
Vese, L., Chan, T.: A multiphase level set framework for image segmentation using the Mumford and shah model. Int. J. Comput. Vis. 50(3), 271–293 (2002)
Zhu, S.C., Yuille, A.: Region competition: unifying snakes, region growing, and Bayes/MDL for multiband image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 18(9), 884–900 (1996)
Rousson, M., Deriche, R.: A variational framework for active and adaptive segmentation of vector values images. In: Proceedings of Workshop on Motion and Video Computing, pp. 56–61 (2002)
Paragios, N., Deriche, R.: Geodesic active regions and level set methods for supervised texture segmentation. Int. J. Comput. Vis. 46, 223–247 (2002)
Duda, R., Hart, P.: Pattern Classification and Scene Analysis. Wiley, New York (1973)
Abd-Almageed, W., Smith, C.E., Ramadan, S.: Kernel snakes: non-parametric active contour models. IEEE Int. Conf. Syst. Man Cybern. 1, 240–244 (2003)
Aubert, A., Barlaud, M., Faugeras, O., Jehan-Besson, S.: Image segmentation using active contours: calculus of variations or shape gradients. SIAM Appl. Math. 63(6), 2128–2154 (2003)
Huang, X., Metaxas, D., Chen, T.: Metamorphs: deformable shape and texture models. In Proceedings of IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, vol. 1, pp. 496–503 (2004)
Mory, B., Ardon, R., Thiran, J.-P.: Variational segmentation using fuzzy region competition and local non-parametric probability density functions. In: IEEE International Conference on Computer Vision (ICCV), Rio, Brazil (2007)
Ni, K., Bresson, X., Chan, T., Esedoglu, S.: Local histogram based segmentation using the Wasserstein distance. Int. J. Comput. Vis. 84, 97–111 (2009)
Kim, J., Fisher, J., Yezzi, A., Cetin, M., Willsky, A.: A nonparametric statistical method for image segmentation using information theory and curve evolution. IEEE Trans. Image Process. 14(10), 1486–1502 (2005)
Yezzi, A., Zollei, L., Kapur, T.: A variational framework for joint segmentation and registration. In Proc. IEEE MMBIA, pp. 44–51 (2001)
Le Guyader, C., Vese, L.: A Combined Segmentation and Registration Framework with a Nonlinear Elasticity Smoother. Lecture Notes in Computer Science, vol. 5567, pp. 600–611 (2009)
Arrate, F., Ratnanather, J.T., Younes, L.: Diffeomorphic active contours. SIAM J. Imaging Sci. 3(2), 176–198 (2010)
Rényi, A.: On measure of dependence. Acta Math. Acad. Sci. Hung. 10, 441–451 (1959)
Shi, J., Chen, Y., Rao, M., Lee, J.S.: A statistical similarity measure for non-rigid multi-modal image registration. Proc. SPIE 7623, 762307 (2010)
Osher, S., Fedkiw, R.: Level Set Methods and Dynamic Implicit Surfaces. Applied Mathematica Sciences, vol. 153. Springer, New York (2002)
Chan, T., Vese, L.: A level set algorithm for minimizing the Mumford-Shah functional in image processing. In: IEEE/Computer Society Proceedings of the 1st IEEE Workshop on “Variational and Level Set Methods in Computer Vision”, pp. 161–168 (2001)
Osher, S., Sethian, J.A.: Fronts propagating with curvature dependent speed: algorithms based on Hamilton-Jacobi formulations. J. Comput. Phys. 79(1), 12–49 (1988)
Chan, T., Wong, C.K.: Total variation blind deconvolution. IEEE Trans. Image Process. 7, 370–375 (1998)
Chan, T.F., Esedoglu, S., Nikolova, M.: Algorithms for finding global minimizers of denoising and segmentation models. SIAM J. Appl. Math. 66, 1632–1648 (2006)
Chambolle, A.: An algorithm for total variation minimization and applications. J. Math. Imaging Vis. 20, 89–97 (2004)
Bresson, X., Esedoglu, S., Vandergheynst, P., Thiran, J.-P., Osher, S.: Fast global minimization of the active contour/snake model. J. Math. Imaging Vis. 28, 151–167 (2007)
Aronszajn, N.: Theory of reproducing kernels. Trans. Am. Math. Soc. 68, 337–404 (1950)
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
In this section, we give the basic theories of RKHS we have used in this paper.
Let E be an arbitrary set and H be a Hilbert space of real functions on E. We say that H is a RKHS if the linear map F x :f→f(x) is a bounded functional for any x∈E.
By this definition, F x ∈H ⋆, which is the dual space of H. Therefore, Reisz representation theorem shows that there exists a unique K x ∈H, such that
Define K:E×E→ℝ as K(x,y)=〈K x (⋅),K y (⋅)〉. It is easy to see that K has the following properties:
-
1.
K is symmetric: K(x,y)=K(y,x).
-
2.
Reproducing property: f(x)=〈K(x,⋅),f(⋅)〉.
-
3.
K is positive definite: \(\sum_{i,j}^{n}a_{i}a_{j}K(x_{i},x_{j})\geq 0\) holds for all x 1,x 2,…,x n ∈E, a 1,a 2,…,a n ∈ℝ and the equality holds if and only if a i =0, i=1,2,…,n.
We call such an K the reproducing kernel for the Hilbert space H.
On the other hand, suppose K:E×E→ℝ is symmetric and positive definite, then according to the Moore-Aronszajn theorem [26], there is a unique Hilbert space of functions on E for which K is a reproducing kernel. In fact, let H 0(E) be the linear span of the functions {K(x,⋅)|x∈E} and define the inner product in H 0(E) to be
Let H(E) be the completion of H 0(E) with respect to this inner product. It is not difficult to check that H(E) is the unique RKHS with reproducing kernel K.
For the particular case E=ℝ. Let C 0(ℝ) be the space of real valued continuous functions vanishing at infinity with the supremum norm. Then we have the following result
where V(ℝ) is the space of all real Borel measurable functions with finite positive variance. This is the main result we have used in this paper and (17), (18) follows directly from this result.
The proof of this result can be obtained through the following three steps (We omit the details here).
-
1.
H 0(ℝ) is dense in C 0(ℝ).
-
2.
Let V(B) be the space of all real bounded Boreal measurable functions, then
$$\sup_{f,g\in V(B)} CC(f(X),g(Y))=\sup_{f,g\in C_0(\mathbb{R})} CC(f(X),g(Y)).$$ -
3.
$$\sup_{f,g\in V(\mathbb{R})} CC(f(X),g(Y))=\sup_{f,g\in V(B)} CC(f(X),g(Y)).$$
Rights and permissions
About this article
Cite this article
Zhang, H., Chen, Y. & Shi, J. Nonparametric Image Segmentation Using Rényi’s Statistical Dependence Measure. J Math Imaging Vis 44, 330–340 (2012). https://doi.org/10.1007/s10851-012-0329-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-012-0329-z