ABSTRACT
In this paper, we proposed an image segmentation model in a variational nonlocal means framework. The model has following advantages. Firstly, Theconvexity global minimize optimum informations are taken into account and got the better segmentation results; secondly, the proposedglobal convex energy functional combined the nonlocal regularization and the local intensity fitting terms. The nonlocal total variational (TV) regularization term can preserve the detail structures of the target objects. At the same time, the modified locally binary fitting (LBF) term introduced to the model as the local fitting term can efficiently deal with the intensity inhomogeneity images; finally, we apply the split Bregman method to minimize the proposed energy functional efficiently. Weapplied the proposed model to the real medical images and extent to sensing images. Comparing with other models, the proposed model not only demonstrates accuracy but also display superiority.
- Kass, M., Witkin, A., and Terzopoulos, D. 1988. Snakes: Active contour models. Int. J. Comput. Vis.. 321--331.Google ScholarCross Ref
- Caselles, V., Kimmel R., and Sapiro, G. 1997. Geodesic active contours. Int. J. Comput. Vis.. 22, 1 (Feb. 1997), 61--80. Google ScholarDigital Library
- Malladi, R., Sethian, J. A., and Vemuri, B. C. 1994. Evolutionary fronts fortopology-independent shape modeling and recovery. In Proc. Eur. Conf. Computer Vision. 3--13. Google ScholarDigital Library
- Kichenassamy, S., Kumar, A., Olver, P., Tannenbaum, A., and Yezzi, A. 1995. Gradient flows and geometric active contour models. In Proc. Int. Conf. Computer Vision, Jun 1995, 810--815. Google ScholarDigital Library
- Osher, S., and Sethian, J. 1988. Fronts propagating with curvature-dependent speed: algorithms based on Hamilton Jacobi formulations. In J. Comput. Phys.. 79(1988), 12--49. Google ScholarDigital Library
- Cohen, L. D., and Cohen, I. Nov. 1993. Finite-element methods for active contourmodels and balloons for 2-d and 3-d images. IEEE Trans. PatternAnal. Mach. Intell. 1131--1147. Google ScholarDigital Library
- Leroy, B., Herlin, I., and Cohen, L. D. 1996. Multi-resolution algorithms foractive contour models. In Proc. 12th Int. Conf. Analysis and Optimizationof Systems. 58--65.Google Scholar
- Xiang, Y., Chung, A. C. S. and Ye, J. 2006. An active contour model forimage segmentation based on elastic interaction. J. Comput. Phys.. 219(Nov. 2006), 455--476. Google ScholarDigital Library
- Xu, C., and Prince, J. 1998. Generalized gradient vector flow external forces for active contours. Signal Process. (Dec. 1998), 131--139. Google ScholarDigital Library
- Leventon, M., Grimson, W., and Faugeraus, O. 2000. Statistical shape influencein geodesic active contours. In Proc. IEEE Conf. Computer Visionand Pattern Recognition. 2000, 316--323.Google Scholar
- Xu, C., and Prince, J. L. 1998. Snakes, shapes, and gradient vector flow. IEEE Trans. Image Process. Mar. 1998, 359--69. Google ScholarDigital Library
- Paragios, N., and Deriche, R. 2002. Geodesic active regions and level setmethods for supervised texture segmentation. Int. J. Comput. Vis.. Feb. 2002, 223--247. Google ScholarDigital Library
- Xie, X., and Mirmehdi, M. 2008. Mac:Magnetostatic active contour model. IEEE Trans. Pattern Anal. Mach. Intell.. 30, 4(2008), 632--646. Google ScholarDigital Library
- Buades, Coll, A. B., and Morel, J. M. 2005. A review of image denoising algorithms with a new one. SIAM Mul. Model. and Simul.. 4, 2(2005), 490--530.Google ScholarCross Ref
- Peyré, G., Bougleux, S., and Cohen, L. 2008. Non-local regularization of inverse problems. ECCV, Part III, LNCS, 5304(2008), 57--68. Google ScholarDigital Library
- Gilboa, G., and Osher, S. 2007. Nonlocal linear image regularization and supervised segmentation. SIAM Mul. Model. and Simul.. 6, 2(2007), 595--630.Google ScholarCross Ref
- Elmoataz, A., Lezoray, O., and Bougleux, S. 2008. Nonlocaldiscrete regularization on weighted graphs: a framework for image and manifold processing. IEEE Trans ImageProcess. 17, 7(2008), 1047--1060. Google ScholarDigital Library
- Bresson, X., and Chan, T. 2008. Non-local unsupervised variational image segmentation models. UCLA CAM Report, 08--67Google Scholar
- Gilboa, G., and Osher, S. 2007. Nonlocal linear image regularization and supervised segmentation. SIAM Multiscale Modeling and Simulation (MMS). 6, 2(2007), 595--630.Google ScholarCross Ref
- Goldstein, T., Osher, S. 2009. Thesplit Bregman method for L1 regularized problems. SIAM J. Imaging Sciences. 2,2(2009), 323--343. Google ScholarDigital Library
- Chan, T. F., and Vese, L. A. 2001. Active contours without edges. IEEE Transactions on Image Processing. 10, 2(2001), 266--277. Google ScholarDigital Library
- Li, C., Xu, C., Gui, C., and Fox, M. D. 2005. Level set evolution without re-initialization: a new variational formulation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). June 2005, 430--436. Google ScholarDigital Library
- Jung, M., Peyré G., Cohen, L. D. 2011. Non-local Active Contours. SSVM, 255--266. Google ScholarDigital Library
- Bresson, X., Esedoglu, S., Vandergheynst, P., Thiran, J., and Osher, S. 2007. Fast Global Minimization of the Active Contour/Snake Models. Journal of Mathematical Imaging and Vision. 28, 2(2007), 151--167. Google ScholarDigital Library
- El-Zehiry, Xu, N., S., Sahoo, P., and Elmaghraby, A. 2007. Graph cut optimization for the Mumford-Shahmodel. In Visualization, Imaging, and Image Processing. Google ScholarDigital Library
Index Terms
- Variational nonlocal image segmentation using split-Bregman
Recommendations
Nonlocal variational image segmentation models on graphs using the Split Bregman
Variational functionals such as Mumford-Shah and Chan-Vese methods have a major impact on various areas of image processing. After over 10 years of investigation, they are still in widespread use today. These formulations optimize contours by evolution ...
Split Bregman method for minimization of region-scalable fitting energy for image segmentation
ISVC'10: Proceedings of the 6th international conference on Advances in visual computing - Volume Part IIIn this paper, we incorporate the global convex segmentation method and the split Bregman technique into the region-scalable fitting energy model. The new proposed method based on the region-scalable model can draw upon intensity information in local ...
Image Segmentation Model Based on Local Image Fitting Energy and Split Bregman Method
ICIG '13: Proceedings of the 2013 Seventh International Conference on Image and GraphicsPDE based image segmentation methods are the state-of-the-art methods due to the high accuracy and continuity of detected edges. Some examples are the region-scalable fitting (RSF) model and the local image fitting energy (LIF) model. But they suffer ...
Comments