Skip to main content Accessibility help

Multi-Phase Texture Segmentation Using Gabor Features Histograms Based on Wasserstein Distance

  • Motong Qiao (a1), Wei Wang (a2) and Michael Ng (a3)


We present a multi-phase image segmentation method based on the histogram of the Gabor feature space, which consists of a set of Gabor-filter responses with various orientations, scales and frequencies. Our model replaces the error function term in the original fuzzy region competition model with squared 2-Wasserstein distance function, which is a metric to measure the distance of two histograms. The energy functional is minimized by alternative minimization method and the existence of closed-form solutions is guaranteed when the exponent of the fuzzy membership term being 1 or 2. We test our model on both simple synthetic texture images and complex natural images with two or more phases. Experimental results are shown and compared to other recent results.


Corresponding author



Hide All
[1]The Berkeley Segmentation Dataset and Benchmark,
[2]Braides, A. and Maso, G. D., Non-local approximation of the Mumford-Shah functional, Calculus of Variations and Partial Differential Equations, 5(4) (1997), 293322.
[3]Bresson, X., Vandergheynst, P. and Thiran, J. P., A variational model for object segmetation using boundary information and shape prior driven by the Mumford-Shah functional, Int. J. Comput. Vision, 68(2) (2006), 145162.
[4]Bresson, X., Esedoglu, S., Vandergheynst, P., Tharan, J. P. and Osher, S., Fast global minimization of the active contour/snake model, J. Math. Imaging Vision, 28 (2007), 151167.
[5]Bae, E., Yuan, J. and Tai, X-C., Global minimization for continuous multiphase partitioning problems using a dual approach, Int. J. Comput. Vision, 92(1) (2011), 112129.
[6]Caselles, V., Geometric models for active contours, International Conference on Image Processing, 3 (1995), 912.
[7]Caselles, V., Kimmel, R. and Sapiro, G., Geodesic active contours, Int. J. Cumput. Vision, 22(1) (1997), 6179.
[8]Chan, T. and Vese, L., Active contours without edges, IEEE Tran. Image Process., 10(2) (2001).
[9]Chan, T., Esedoglu, S. and Nikolova, M., Algorithms for finding global minimizers of image segmentation and denoising models, SIAM J. Appl. Math., 66(5) (2006), 16321648.
[10]Chan, T., Sandberg, B. and Vese, L., Active contours without edges for vector-valued images, J. Visual Commun. Image Representation, 11(2) (2000), 130141.
[11]Chan, T., Esedoglu, S. and Ni, K., Histogram based segmentation using wasserstein distances, scale space and variational methods in computer vision, Lecture Notes in Computer Science, 4485 (2007), 697708.
[12]Chambolle, A., Image segmentation by variational methods: Mumford and Shah functional and the discrete approximations, SIAM J. Appl. Math., 55(3) (1995), 827863.
[13]Chambolle, A., An algorithm for total variation minimization and application, J. Math. Image Vision, 20 (2004), 8997.
[14]Chung, G. and Vese, L., Image segmentation using a multilayer level-set approach, Comput. Visual. Science, 12(6) (2009), 267285.
[15]Cohen, L. D., On active contour models and balloons, CVGIP: Image Understanding, 53(2) (1991), 211218.
[16]Georgiou, T., Michailovich, O., Rathi, Y., Malcolm, J. and Tannenbaum, A., Distribution metrics and image segmentation, Linear Algebra and Its Applications, 405 (2007), 663672.
[17]Gobbino, M., Finite difference approximation of the Mumford-Shah functional, Commun. Pure Appl. Math., 51(2) (1998), 197228.
[18]Goldenberg, R., Kimmel, R., Rivlin, E. and Rudzsky, M., Fast geodesic active contours, IEEE Tran. Image Process., 10(10) (2001), 14671475.
[19]Houhou, N. and Thiran, J. P., Fast texture segmentation model based on the shape operator and active contour, IEEE Conference on Computer Vision and Pattern Recognition, 1-8, 2008.
[20]Houhou, N., Thiran, J. P. and Bresson, X., Fast texture segmentation based on semi-local region descriptor and active contour, Numer. Math. Theory Meth. Appl., 2(4) (2009), 445468.
[21]Huang, Y., Ng, M. K. and Wen, Y. W., A fast total variation minimization method for image restoration, Multiscale Model. Simul., 7 (2008), 774795.
[22]Jain, A. K. and Farrokhnia, F., Unsupervised texture segmentation using gabor filters, Pattern Recognition, 24(12) (1991), 11671186.
[23]Kass, M., Witkin, A. and Terzopoulos, D., Snakes: active contour models, Int. J. Comput. Vision, 1 (1988), 321331.
[24]Kantorovich, L., On the translocation of masses, C. R. (Doklady) Acad. Sci. URSS (N.S.), (37) (1942), 199201.
[25]Kichenassamy, S., Gradient flows and geometric active contour models, 5th International Conference on Computer Vision, 810815, 1995.
[26]Klir, G. J. and Yuan, B., Fuzzy Sets and Fuzzy Logic: Theory and Applications, Prentice Hall, ISBN 978-0-13-101171-7, 1995.
[27]Lie, J., Lysaker, M. and Tai, X. C., A binary level set model and some applications to Mumford-Shah image segmentation, IEEE Trans. Image Processing, 15(5) (2006), 11711181.
[28]Lie, J., Lysaker, M. and Tai, X. C., Piecewise constant level set methods and image segmentation, Scale Space and PDE Methods in Computer Vision, 3459 (2005), 573584.
[29]Li, F., Ng, M. K., Zeng, T. Y. and Shen, C., A multiphase image segmentation method based on fuzzy region competition, SIAM J. Image. Sciences, 3(3) (2010), 277299.
[30]Li, F. and Ng, M. K., Kernel density estimation based multiphase fuzzy region competition method for texture image segmentation, Commun. Comput. Phys., 8 (2010), 623641.
[31]Li, W., Mao, K., Zhang, H. and Chai, T., Selection of gabor filters for improved texture feature extraction, Proceedingsof IEEE 17th International Conferenceon Image Processing, 361364, 2010.
[32]Ma, L. Y. and Yu, J., Texture segmentation based on local feature histograms, 18th IEEE International Conference on Image Processing, ICIP 2011, 33493352, 2011.
[33]Michailovich, O., Rathi, Y. and Tannenbaum, A., Image segmentation using active contours driven by the Bhattacharyya gradient flow, IEEE Tran. Image Process., 16(11) (2007).
[34]Mory, B. and Ardon, R., Variation segmentation using fuzzy region competition and local non-parametric probability density funtions, 11th IEEE International Conference on Computer Vision, ICCV 2007, 18, 2007.
[35]Mory, B. and Ardon, R., Fuzzy region competition: a convex two-phase segmentation framework, scale space and variational methods in computer vision, Lecture Notes in Computer Science, 4485 (2007), 214226, 2007.
[36]Mumford, D. and Shah, J., Optimal approximation by piecewise smooth functions and associated variational problems, Commun. Pure Appl. Math., 42 (1989), 577685.
[37]Ni, K., Bresson, X., Chan, T. and Esedoglu, S., Local histogram based segmentation using the Wasserstein distance, Int. J. Comput. Vision, 84(1) (2009), 97111.
[38]Osher, S. and Sethian, J. A., Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulation, J. Comput. Phys., 79 (1998), 1249.
[39]Paragios, N. and Deriche, R., Geodesic active regions and level set methods for supervised texture segmentation, Int. J. Comput. Vision, 46(3) (2002), 223247.
[40]Rachev, S. and Ruschendorf, L., Mass Transportation Problems, Vol. I: Theory, Vol. II: Applications Probability and Its Applications, Springer-Verlag, New York, 1998.
[41]Sandberg, B., Chan, T. and Vese, L., A level-set and gabor based active contour algorithm for segmenting textured images, UCLA Comput. Appl. Math., Rep. 02-39, 2002.
[42]Sagiv, C., Sochen, N. A. and Zeevi, Y. Y., Integrated active contours for texture segmentation, IEEE Tran. Image Process., 15(6) (2006).
[43]Sagiv, C., Sochen, N. A. and Zeevi, Y. Y., Geodesic active contours applied to texture feature space, Proc. Scale-Space and Morphology in Computer Vision, Kerckhove, M., Ed. Berlin, Germany: Springer-Verlag, 2106 (2001), 344352.
[44]Thomas, B. and Daniel, C., On local region models and a statistical interpretation of the piece-wise smooth Mumford-Shah functional, Scale Space and Variational Methods in Computer Vision, 4485 (2007), 203213.
[45]Vese, L. and Chan, T., A multiphase level set framework for image segmentation using the Mumford and Shah Model, Int. J. Comput. Vision, 50(3) (2002), 271293.
[46]Wang, Y., Xiong, Y., Lv, L., Zhang, H., Cao, Z. and Zhang, D., Vector-valued Chan-Vese model driven by local histogram for texture segmentation, 17th IEEE International Conference on Image Processing, ICIP 2010, 645648, 2010.
[47]Xie, X., Level set based segmentation using local feature distribution, 2010 International Conference on Pattern Recognition, 2010.
[48]Yuan, H. and Zhang, X. P., Texture image retrieval based on a gaussian mixture model and similarity measure using a kullback divergence, IEEE International Conference on Multimedia and Expo, 2004.
[49]Yuan, J., Bae, E., Tai, XC. and Boykov, Y., A continuous max-flow approach to Potts model, Computer Vision–ECCV 2010, 379392, 2010.
[50]Zhu, S. C. and Yuille, A. L., A unified theory for image segmentation: region competition and its analysis, Harvard Robotics Laboratory Technical Report 95-7, 1995.
[51]Zhu, S. C. and Yuille, A. L., Region competition: unifying snakes, region growing and Bayes/MDL for multi-band image segmentation, IEEE Trnas. Pattern Anal. Machine Intell., 18 (1996), 884900.



Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed