This study proposes an improved level set method for segmenting images with intensity inhomogeneity. One of the improvements is to consider the difference between an original image and an estimated image without bias field in the image model. Apart from using this difference, Gaussian distribution with means and variance is utilised as the local intensity descriptor to map the original image into another domain so the object and the background can be better separated in the transformed domain. Then, an improved level set energy function that combines the image term, local variance, and the above difference is defined. The minimisation of the function can be processed by level set evolution. The proposed method is compared with existing methods, and experiments on both synthetic and real images demonstrate that authors’ method has superior performance.

References

1. 1)
  - 12. Rousson, M., Brox, T., Deriche, R.: ‘Active unsupervised texture segmentation on a diffusion based feature space’. Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, Madison, USA, June 2003, pp. 699–704.
2. 2)
  - 25. Li, C.M., Xu, C.Y., Gui, C.F.: ‘Distance regularized level set evolution and its application to image segmentation’, IEEE Trans. Image Process., 2010, 19, (20), pp. 3243–3254.
3. 3)
  - 20. Wang, X.F., Min, H., Zou, L., et al: ‘A novel level set method for image segmentation by incorporating local statistical analysis and global similarity measurement’, Pattern Recognit., 2015, 48, (1), pp. 189–204.
4. 4)
  - 15. Vasilevskiy, A., Siddiqi, K.: ‘Flux-maximizing geometric flows’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, (12), pp. 1565–1578.
5. 5)
  - 7. Cremers, D., Kohlberger, T., Schnorr, C.: ‘Shape statistics in kernel space for variational image segmentation’, Pattern Recognit., 2003, 36, (9), pp. 1929–1943.
6. 6)
  - 13. Brox, T., Rousson, M., Deriche, R.: ‘Colour, texture, and motion in level set based segmentation and tracking’, Image Vis. Comput., 2010, 28, (3), pp. 376–390.
7. 7)
  - 9. Chan, T., Zhu, W.: ‘Level set based shape prior segmentation’. Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, San Diego, USA, June 2005, pp. 1164–1170.
8. 8)
  - 5. Zhan, T.M., Zhang, J., Xiao, L., et al: ‘An improved variational level set method for MR image segmentation and bias ﬁeld correction’, Magn. Reson. Imaging, 2013, 31, (3), pp. 439–447.
9. 9)
  - 24. Huang, C.C., Zeng, L.: ‘An active contour model for the segmentation of images with intensity inhomogeneities and bias field estimation’, PloS One, 2015, 10, (3), pp. 1–24.
10. 10)
  - 21. Michailovich, O., Rathi, Y., Tannenbaum, A.: ‘Image segmentation using active contours driven by the Bhattacharyya gradient flow’, IEEE Trans. Image Process., 2007, 16, (11), pp. 2787–2801.
11. 11)
  - 1. Boykov, Y., Jolly, M.P., Roberts, E.F.: ‘Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images’. Proc. IEEE Int. Conf. Computer Vision, Vancouver BC, Canada, July 2001, pp. 105–112.
12. 12)
  - 14. Caselles, V., Kimmel, R., Sapiro, G.: ‘Geodesic active contours’, Int. J. Comput. Vis., 1997, 22, (1), pp. 61–79.
13. 13)
  - 3. Chan, T., Vese, L.: ‘Active contours without edges’, IEEE Trans. Image Process., 2001, 10, (2), pp. 266–277.
14. 14)
  - 19. Wang, X.F., Min, H., Zhang, Y.G.: ‘Multi-scale local region based level set method for image segmentation in the presence of intensity inhomogeneity’, Neurocomputing, 2015, 151, pp. 1086–1098.
15. 15)
  - 11. Paragios, N., Deriche, R.: ‘Geodesic active regions and level set methods for supervised texture segmentation’, Int. J. Comput. Vis., 2002, 46, (3), pp. 223–247.
16. 16)
  - 4. Ning, J.F., Zhang, L., Zhang, D., et al: ‘Interactive image segmentation by maximal similarity based region merging’, Pattern Recognit., 2010, 43, (2), pp. 445–456.
17. 17)
  - 17. Wang, X.F., Huang, D.S., Xu, H.: ‘An efficient local Chan–Vese model for image segmentation’, Pattern Recognit., 2010, 43, (3), pp. 603–618.
18. 18)
  - 23. Li, C.M., Huang, R., Ding, Z.H., et al: ‘A level set method for image segmentation the presence of intensity inhomogeneities with application to MRI’, IEEE Trans. Image Process., 2011, 20, (7), pp. 2007–2016.
19. 19)
  - 10. Chen, F., Yu, H.M., Hu, R., et al: ‘Deep leaning shape priors for object segmentation’. Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, Portland, OR, USA, June 2013, pp. 1870–1877.
20. 20)
  - 2. Kass, M., Witkin, A., Terzopoulos, D.: ‘Snakes: active contour models’, Int. J. Comput. Vis., 1987, 1, (4), pp. 321–331.
21. 21)
  - 8. Cremers, D., Schmidt, F.R., Barthel, F.: ‘Shape priors in variational image segmentation: convexity, Lipschitz continuity and globally optimal solutions’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Anchorage, USA, June 2008, pp. 1–6.
22. 22)
  - 6. Zhang, K.H., Zhang, L., Lam, K.M., et al: ‘A level set approach to image segmentation with intensity inhomogeneity’, IEEE Trans. Cybern., 2016, 46, (2), pp. 546–557.
23. 23)
  - 16. Mumford, D., Shah, J.: ‘Optimal approximation by piecewise smooth functions and associated variational problems’, Commun. Pure Appl. Math, 1989, 42, pp. 577–685.
24. 24)
  - 22. Sum, K.W., Cheung, P.Y.S.: ‘Vessel extraction under non-uniform illumination: a level set approach’, IEEE Trans. Biomed. Eng., 2015, 55, (1), pp. 358–360.
25. 25)
  - 18. Xie, X.M., Wang, C.M., Zhang, A.J., et al: ‘A robust level set method based on local statistical information for noisy image segmentation’, Optik, 2014, 125, pp. 2199–2204.

Level set method for image segmentation based on local variance and improved intensity inhomogeneity model

References

Related content