Home / Current Issue / Paper 1700217
CONTRAST DRIVEN ELASTICA FOR IMAGE SEGMENTATION
Subject area: Science,Engineering and Technology · Area of research: IMAGE PROCESSING
Abstract
Minimization of boundary curvature is a classic regularization technique for image segmentation in the presence of noisy image data. Gradient descent methods have been used for deriving the techniques for minimizing curvature which could be trapped by a local minimum and, therefore, required a good initialization. Recently, this barrier has been overcome by the combinatorial optimization techniques by providing solutions that can achieve a global optimum. However, when the true object has high curvature regularization methods can fail. In these circumstances, existing methods depend on a data term to overcome the high curvature of the object. Unfortunately, these methods fail when the data term is unambiguous in some images. So in order to eliminate these problems, we propose a contrast driven elastic model (including curvature), which can accommodate high curvature objects and an ambiguous data model. We demonstrate that we can accurately segment extremely challenging synthetic and real images with ambiguous data discrimination, poor boundary contrast, and sharp corners. By using this method we have provided a quantitative evaluation of our segmentation approach when these are applied to a standard image segmentation data set.
Keywords
Euler elastic, weighted curvature, combinatorial optimization, primal formulation, image segmentation.
References
[1] E. Bae , J. Shi, and , X,-C.Tai,”Graph cuts for curvature based image denoising” IEEE Trans , Image Process , Vol.20 , no . 5, pp.1199-1210
[2] X.Bai and G. Sapiro , “A geodesic framework for fast interactive image and video segmentation and matting” in Proc. ICCV , Rio de Jameiro Brazil, 2007, pp.1-8.
[3] A.Blake , C. Rother , M.Brown , P.Perez , and P.Torr , “Interactive image segmentation using an adaptive GMMRF model” , in proc ECCV , 2004, PP.428-441.
[4] Y.Boykov and M.-P.Jolly , “Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images,”in proc. ICCV , 2001,PP.105-112.
[5] Y.Boykov and V.Kolmogorov , “Computing geodisics and minimal surfaces via graph cuts ,” in proc. ICCV , Oct . 2003,pp.26-33.
[6] A.M.Bruckstein ,A.N.Netravali ,and T.J.Richardson , “Epiconvergence of discrete elastica “, Apple , Anal., Vol.79 , nos , 1-2 , pp.137-171,2001.
[7] V.Caselles , R.Kimmel , and G.Sapiro , “Geodesic active contours” , Int , J. Compt .Vis., Vol.22 , no.1 , pp.61-79 , 1997.
[8] T.F.Chan and L.A Vese,”Active contours without edges,” IEEE Trans. Image process., Vol.10 , no.2 , pp. 266-277 , Feb , 2001.
[9] C.Coupire , L.Grady , L.Najman , and H.Talbot , “Power water shed. A Unfying graph based optimization framework,” IEEE Trans .Pattern Anal. Mach. Intell ., Vol.30 , no . 7 , pp.1384-1399 , Jul.2001.
[10] .N.Y.El-Zehiry and L.Grady “Fast global optimization of curvature ,” in proc. CVPR, 2010 pp. 3257-3264.
[11] N.El-Zehiry and L.Grady , “Optimization of weighted curvature for image segmentation,” cvRR ,2010,[online].Available http://arxiv.org/pdf/1006.4175.pdf .
[12] S.Esedoglu and J.Shen , “Digital inpainting based on the Mumford shah Euler image model,” Eur.J.Appl.Math .,Vol.13 , no.4 , pp.353-370 , 2002.
[13] G.Funka- Lea et al.,”Automatic heart isolation for CT coronary visualization using graph – cuts,” in proc . ISBI , Apr.2006 , pp.614-617.
[14] L.Grady,“Random walks for image segmentation,”IEEE Trans.pattern Anal.Mach . Intell.,Vol.28 , no.11 , pp.1768- 1783 , Nov.2006.
[15] I.H,Jermy and H.Ishikawa , “Globally optimal regions and boundaries as minimum ratio weight cycles.” IEEE Trans. Pattern Anal.Mach.Intell.,Vol.23 , no.10 , pp.1075- 1088 , oct , 2001
[16] M.Kass , A. Witkin and D.Terzopoulos , “snakes:Active contour models,” Int.J.comput. Vis.,Vol.1.no.4 , pp.321-331 , 1988
[17] V.Kolmogorov and C.Rothore , “Minimizing nonsubmodular functions with graph cuts – A review,” IEEE Trans. Pattern Anal.Mach.Intell.,Vol.29 , no.7 , pp.1274- 1279 , Jul.2007.
[18] V.Kolmogorov and R.Zabin, “what energy functions can be minimized via graph cuts 2,” IEEE Trans.pattern Anal.Mach Intell.,Vol.26 , no.2 , pp.147-159 , Feb.2004.
[19] M.Kruger , P.Dennice and G.Gimel’farb , “Robust and efficient object segmentation using pseudo-elastica,” Pattern Recognit. Lett., Vol.34 , no.8 , pp.833-845 , 2013.[online]Available http://dx. 10.1016/j.patrec.2012.12.017
[20] D.Mumford , “Elastica and computer vision,” in algebraic geometry and its applications.Springer , 1994 , pp.491-506.
[21] C.Rother , L.Kolmogrov and A.Blake, “‘Grab cut’:interactive foreground extraction using intred graph cuts,” in proc.SIGGRAPH , 2004, pp.309-314.
[22] C.Rother , L.Kolmogrov V.Lemptysky and M.Szummer , “Optimizing binary MRFs via extended roof duality,” in proc .CVPR, 2007, PP.1-8.
[23] T.Schoenemann and D.Cremers, “introducing curvature into globally optimal image segmentation: Minimum ratio cycles on product graps,” in proc. IEEE 11th ICCV , oct , 2007 , pp.1-7.
[24] T.Schonemann , F.Kahl , and D. Cremers, “curvature regularity for region- based image segmentation and inpainting : A Linear programming relaxation,” in Proc . ICCV , Kyoto , Japan , 2009 , pp.17-23.
[25] T.Schonemann , S.Masnou , and D.Cremers , “The elastic ratio : Introdusing curvature into ratio-based image segmentation,” IEEE Trans , Image process.,Vol.22 , no.9 , pp.2565-2581 , sep.2011.
[26] J Shen , S.H.Kang , and T.F. Chan , “Euler’s elastic and curvature based inpainting,” SIAM J. Appl . Math., Vol 63 , no.2 , pp. 564- 592 , 2003.
[27] X.Tai , J.Hahn , and G.J Chang , “ Atleast algorithm for Euler’s elastic model using argumented Lagrangian method,” SHAM J.Image.sci.,Vol.4 , no.1 , pp.313-344 , 2011.
[28] P.Wighton , M.Sadeghi , T.K..Lee and , M.S.Atkins , “A fully automatic random walker segmentation for skin lesions in a supervised setting ,” in proc.MICCAI , 2009 , pp.1108-1115.
[29] W.Zhu , X.Tai , and T.Chan , “Image segmentation using Euler’s elastic as the regularization,” J.Sci. comput.,Vol . 57 , no.2 , pp.414-430 , 2013.
How to cite this paper
@article{1700217,
author = {MADHAVI LATHA PARSA, SINDHU MARUMUDI, NAVYA KODURU, AKHILA PATIBANDLA, M. R. N. TAGORE},
title = {CONTRAST DRIVEN ELASTICA FOR IMAGE SEGMENTATION},
journal = {Iconic Research And Engineering Journals},
year = {2018},
volume = {1},
number = {8},
pages = {95-102},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1700217.pdf},
abstract = {Minimization of boundary curvature is a classic regularization technique for image segmentation in the presence of noisy image data. Gradient descent methods have been used for deriving the techniques for minimizing curvature which could be trapped by a local minimum and, therefore, required a good initialization. Recently, this barrier has been overcome by the combinatorial optimization techniques by providing solutions that can achieve a global optimum. However, when the true object has high curvature regularization methods can fail. In these circumstances, existing methods depend on a data term to overcome the high curvature of the object. Unfortunately, these methods fail when the data term is unambiguous in some images. So in order to eliminate these problems, we propose a contrast driven elastic model (including curvature), which can accommodate high curvature objects and an ambiguous data model. We demonstrate that we can accurately segment extremely challenging synthetic and real images with ambiguous data discrimination, poor boundary contrast, and sharp corners. By using this method we have provided a quantitative evaluation of our segmentation approach when these are applied to a standard image segmentation data set. },
keywords = {Euler elastic, weighted curvature, combinatorial optimization, primal formulation, image segmentation.},
month = {February},
}