Hostname: page-component-7b7567c8c-lpg2g Total loading time: 0 Render date: 2026-11-15T09:57:21.514Z Has data issue: false hasContentIssue false
  • English
  • Français

Integrating Feature Direction Information with a Level Set Formulation for Image Segmentation

Part of:Optics, electromagnetic theory - General

Published online by Cambridge University Press:  27 January 2016

Meng Li and
Yi Zhan
Meng Li*
Affiliation:
Department of Mathematics, Key Laboratory of Group & Graph Theories and Applications, Chongqing University of Arts and Sciences, Yongchuan Chongqing 402160, China
Yi Zhan
Affiliation:
College of Mathematics and Statistics, Chongqing Technology and Business University, Chongqing 400067, China
*
*Corresponding author. Email address:limeng7319@163.com (M. Li)

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

A feature-dependent variational level set formulation is proposed for image segmentation. Two second order directional derivatives act as the external constraint in the level set evolution, with the directional derivative across the image features direction playing a key role in contour extraction and another only slightly contributes. To overcome the local gradient limit, we integrate the information from the maximal (in magnitude) second-order directional derivative into a common variational framework. It naturally encourages the level set function to deform (up or down) in opposite directions on either side of the image edges, and thus automatically generates object contours. An additional benefit of this proposed model is that it does not require manual initial contours, and our method can capture weak objects in noisy or intensity-inhomogeneous images. Experiments on infrared and medical images demonstrate its advantages.

Keywords

Image segmentationlevel set evolutionvariational modelimage featuremaximal second-order directional derivative

MSC classification

Secondary:78A48: Composite media; random media

Information

Type
Research Article
Information
East Asian Journal on Applied Mathematics , Volume 6 , Issue 1 , February 2016, pp. 1 - 22
Copyright
Copyright © Global-Science Press 2016 

References

[1]Papoutsakis, K.E. and Argyros, A.A., Integrating tracking with fine object segmentation, Image Vision Comp. 31, 771–785 (2013).Google Scholar
[2]Bagci, U., Chen, X. and Udupa, J.K., Hierarchical scale-based multiobject recognition of 3-D anatomical structures, IEEE Trans. Medical imaging 31, 777–789 (2012).Google Scholar
[3]Aja-Fernández, S., Curiale, A.H. and Vegas-Sánchez-Ferrero, G., A local fuzzy thresholding methodology for multiregion image segmentation, Knowledge-Based Systems 83, 1–12 (2015).Google Scholar
[4]Li, Y., Wavelet-based fuzzy multiphase image segmentation method, Pattern Recognition Letts. 53, 1–8 (2015).Google Scholar
[5]Medeiros, R.S., Scharcanski, J. and Wong, A., Image segmentation via multi-scale stochastic regional texture appearance models, Comput. Vis. Image Und. in press, doi:10.1016/j.cviu.2015.06.001.CrossRefGoogle Scholar
[6]Yang, Y., Han, S., Wang, T., Tao, W. and Tai, X., Multilayer graph cuts based unsupervised color-texture image segmentation using multivariate mixed student's t-distribution and regional credibility merging, Pattern Recognition 46, 1101–1124 (2013).Google Scholar
[7]Caselles, V., Kimmel, R. and Sapiro, G., Geodesic active contours, Int. J. Comp. Vision 22, 61–79 (1997).Google Scholar
[8]Chan, T. and Vese, L., Active contours without edges, IEEE Trans. Image Proc. 10, 266–277 (2001).CrossRefGoogle ScholarPubMed
[9]Li, C., Xu, C., Gui, C. and Fox, M.D., Level set formulation without re-initialization: A new vari-ational formulation, in Proc. IEEE Conf. Comp. Vision Pattern Recognition (CVPR), vol. 1, pp. 430–436 (2005).Google Scholar
[10]Wu, Y. and He, C., A convex variational level set model for image segmentation, Signal Processing 106, 123–133 (2015).Google Scholar
[11]Osher, S. and Sethian, J.A., Fronts propagating with curvature dependent speed: Algorithms based on Hamilton-Jacobi formulations, J. Comput. Phys. 79.12–49 (1988).Google Scholar
[12]Li, C., Kao, C., Gore, J.C. and Ding, Z., Minimization of region-scalable fitting energy for image segmentation, IEEE Trans. Image Proc. 17, 1940–1949 (2008).Google ScholarPubMed
[13]Li, C., Huang, R., Ding, Z., Gatenby, J.C., Metaxas, D.N. and Gore, J.C., A level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI, IEEE Trans. Image Proc. 20, 2007–2015 (2011).Google Scholar
[14]Zhu, W., Tai, X. and Chan, T., Image segmentation using Euler's elastica as the regularization, J. Sci. Comput. 57, 414–438 (2013).Google Scholar
[15]Liu, W., Shang, Y. and Yang, X., Active contour model driven by local histogram fitting energy, Pattern Recognition Letts. 34, 655–662 (2013)Google Scholar
[16]Li, M., He, C.J. and Zhan, Y., Adaptive level-set evolution without initial contours for image segmentation, J. Electronic Imaging 20, 023004 (2011).Google Scholar
[17]Li, M., He, C.J. and Zhan, Y., Tensor diffusion level set method for infrared targets contours extraction, Infrared Phys. & Tech. 55, 19–25 (2012).Google Scholar
[18]Kimmel, R., and Bruckstein, A.M., Regularized Laplacian zero crossings as optimal edge integrators, Int. J. Comp. Vision 53, 225–243 (2003).CrossRefGoogle Scholar
[19]Paragios, N., Mellina-Gottardo, O. and Ramesh, V., Gradient vector flow fast geometric active contours, IEEE Trans. Pattern Anal. Machine Intelligence 26, 402–407 (2004).Google Scholar
[20]Ersoy, I., Bunyak, F., Mackey, M.A. and Palaniappan, K., Cell segmentation using hessian-based detection and contour evolution with directional derivatives, in: 15th IEEE Int. Conf. Image Proc. (ICIP), San Diego, pp. 1804–1807 (2008).Google Scholar
[21]Melonakos, J., Pichon, E., Angenent, S. and Tannenbaum, A., Finsler active contours, IEEE Trans. Pattern Anal. Machine Intelligence 30, 412–423 (2008).CrossRefGoogle ScholarPubMed
[22]Luo, Z. and Wu, J., The integration of directional information and local region information for accurate image segmentation, Pattern Recognition Letts. 32, 1990–1997 (2011).Google Scholar
[23]Li, C., Kao, C., Gore, J.C. and Ding, Z., Implicit active contours driven by local binary fitting energy, in Proc. IEEE Conf. Comp. Vision Pattern Recognition (CVPR), IEEE Computer Society, Washington, DC, pp. 1–7 (2007).Google Scholar
[24]Gallego, G., Ronda, J.I. and Valdés, A., Directional geodesic active contours, in 19th IEEE Int. Conf. Image Proc. (ICIP), Orlando, pp. 2561–2564 (2012).Google Scholar
[25]Estellers, V., Zosso, D., Bresson, X. and Thiran, J., Harmonic active contours, IEEE Trans. Image Proc. 23, 69–82 (2014).Google Scholar
[26]Carmona, R.A., and Zhong, S., Adaptive smoothing respecting feature directions, IEEE Trans. Image Proc. 7, 353–358 (1998).Google Scholar
[27]Gonzalez, R.C. and Woods, R.E., Digital Image Processing, Second Edition. Prentice-Hall, New Jersey (2002).Google Scholar
[28]Shattuck, D.W., Sandor-Leahy, S.R., Schaper, K.A., Rottenberg, D.A. and Leahy, R.M., Magnetic resonance image tissue classification using a partial volume model, NeuroImage 13, 856–876 (2001).Google Scholar
[29]Liu, B., Cheng, H.D., Huang, J., Tian, J., Tang, X. and Liu, J., Probability density difference-based active contour for ultrasound image segmentation, Pattern Recognition 43, 2028–2042 (2010).Google Scholar