Region-Based Level Set Model for Image Segmentation

Abstract:

To reduce the impact of intensity inhomogeneity to image segmentation, a region-based level set (RBLS) model was proposed in this study. Its energy functional consists of four terms: local term, area term, length term and penalty term. The proposed model utilizes both global image information and local image information, and by using the local image information, the image with intensity inhomogeneity can be efficiently segmented. In addition, the global implementation of our RBLS model is introduced. It can detect all of the targets in the image. The experimental results showed that the proposed model can segment the image with intensity inhomogeneity efficiently, which is better than that of CV model.

• Periodical: Advanced Materials Research (Volumes 616-618)
• Pages: 2223-2228
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.616-618.2223
• Online since: December 2012
• Authors: Da Chuan Wei
• Keywords: CV Model, Global Implementation, Image Segmentation, Region-Based Level Set (RBLS) Model

References

[1] V. Caselles, F. Catte, T. Coll, and F. Dibos. A geometric model for active contours in image processing. Numer Math, Vol. 66, No. 1(1993), pp.1-31.

DOI: 10.1007/bf01385685

[2] V. Caselles, R. Kimmel, and G. Sapiro. Geodesic active contours. International Journal of Computer Vision, Vol. 22, No. 1(1997), pp.61-79.

DOI: 10.1109/iccv.1995.466871

[3] C.M. Li, C.Y. Xu, C.F. Gui, and M.D. Fox. Level set evolution without re-initialization: A new variational formulation. IEEE International Conference on Computer Vision and Pattern Recognition, Vol.1[C].San Diego: IEEE Computer Society Press, (2005), pp.430-436.

DOI: 10.1109/cvpr.2005.213

[4] D. Mumford, J. Shah. Optimal approximation by piecewise smooth functions and associated variational problems. Communications on Pure and Applied Mathematics, Vol. 42, No. 5(1989), pp.577-685.

DOI: 10.1002/cpa.3160420503

[5] T.F. Chan, L.A. Vese. Active contours without edges. IEEE Trans. on Image Processing, Vol. 10, No. 2(2001), pp.266-277.

DOI: 10.1109/83.902291

[6] L.A. Vese, T.F. Chan. A multiphase level set framework for image segmentation using the Mumford and Shah model. International Journal of Computer Vision, Vol. 50, No. 3(2002), pp.271-293.

[7] A. Tsai, A. Yezzi, and A.S. Willsky. Curve evolution implementation of the Mumford-Shah functional for image segmentation, denoising, interpolation, and magnification. IEEE Trans. on Image Processing, Vol. 10, No. 8(2001), pp.1169-1186.

DOI: 10.1109/83.935033

[8] C.M. Li, C.Y. Kao, J.C. Gore, and Z.H. Ding. Implicit active contours driven by local binary fitting energy. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition '07 [C], Washington D C, 1-7(2007).

DOI: 10.1109/cvpr.2007.383014

[9] C.M. Li, C.Y. Kao, J.C. Gore, and Z.H. Ding. Minimization of region-scalable fitting energy for image segmentation. IEEE Trans. on Image Processing, Vol. 17, No. 10(2008), pp.1940-1949.

DOI: 10.1109/tip.2008.2002304

[10] L. Wang, C. Li, Q. Sun, D. Xia, and C.Y. Kao. Active contours driven by local and global intensity fitting energy with application to brain MR image segmentation. Computerized Medical Imaging and Graphics, Vol. 33, No.7(2009), pp.520-531.

DOI: 10.1016/j.compmedimag.2009.04.010