A More Robust Active Contour Model with Group Similarity
Image segmentation based on active contour model has been widely used in recent years. However, in real application, image segmentation results are always leaded to corrupt because of partial missing of target boundaries or some misleading factors. In order to solve the issue, Zhou proposed a model called active contour with group similarity. But Zhou’s model is purely based on global information of image and cannot deal with image segmentation with intensity inhomogeneity. In order to optimize Zhou’s model and make it more robust, we construct a new energy function which combines global feature with local feature of image. The local feature can solve the issue of image segmentation with intensity inhomogeneity. And the global feature can make our model less sensitive to the initial position of the curve or noise. The experiment results have proved that, our method can achieve satisfying segmentation results on image segmentation with intensity inhomogeneity and show less sensitive to the initial position of the curve.
KeywordsCV model LBF model Group similarity Robust Global information Local information
This work was supported by the National Key Technology Support Program of China (No. 2015BAF04B00), The Fundamental Research Funds for the central Universities, and the Shanghai Innovation Action Project of Science and Technology (15DZ1101202).
- 5.Li, C., Kao, C.Y., Gore, J.C., et al.: Implicit active contours driven by local binary fitting energy. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1–7. DBLP (2007)Google Scholar
- 8.Zhou, X., Huang, X., Duncan, J.S., et al.: Active contours with group similarity. pp. 2969–2976 (2013)Google Scholar
- 9.Li, C., Xu, C., Gui, C., et al.: Level set evolution without re-initialization: a new variational formulation. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 430–436. IEEE Xplore (2005)Google Scholar
- 12.Nesterov, Y.: Gradient methods for minimizing composite objective function (2007)Google Scholar
- 14.Leventon, M.E., Grimson, W.E.L., Faugeras, O.: Statistical shape influence in geodesic active contours. In: IEEE Conference on Computer Vision and Pattern Recognition, 2000 Proceedings, vol. 1, pp. 316–323. IEEE (2000)Google Scholar
- 16.Tsai, A., Yezzi, A., Wells, W., et al.: Model-based curve evolution technique for image segmentation. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, vol. 1, pp. I-I. IEEE (2001)Google Scholar
- 17.Etyngier, P., Segonne, F., Keriven, R.: Shape priors using manifold learning techniques. In: IEEE 11th International Conference on Computer Vision, ICCV 2007, pp. 1–8. IEEE (2007)Google Scholar
- 19.Riklin-Raviv, T., Kiryati, N., Sochen, N.: Prior-based segmentation by projective registration and level sets. In: Tenth IEEE International Conference on Computer Vision, ICCV 2005, vol. 1, pp. 204–211. IEEE (2005)Google Scholar
- 20.Lv, P., Zhao, Q., Gu, D.: Segmenting similar shapes via weighted group-similarity active contours. In: IEEE International Conference on Image Processing, pp. 4032–4036. IEEE (2015)Google Scholar
- 24.Fazel, M.: Matrix rank minimization with applications. Ph. D. thesis, Stanford University (2002)Google Scholar