Advertisement

A Level Set Method for Natural Image Segmentation by Texture and High Order Edge-Detector

  • Yutao Yao
  • Ziguan CuiEmail author
  • Feng Liu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11935)

Abstract

Active contour model has been a widely used methodology in image segmentation. However, due to the texture complexity of natural images, it unavoidably faces many difficulties. In this paper, we propose a novel method to accurately segment natural images by texture and high order edge-detector. Firstly, we calculate local covariance matrix which is estimated from image gradient information within the local window, and use the eigenvalues of matrix to describe local texture feature of the image. Then, in order to suppress the effect of perplexing background, we introduce a high order edge-detector which can eliminate the background as much as possible while it can save the object boundary. Finally, the intensity term, texture term and edge-detector term are incorporated into the level set method to segment natural images. The proposed method has been tested on many natural images, and experimental results show the segmentation performance of the proposed method is better than prior similar state-of-the-art methods.

Keywords

Active contour model Level set Natural image segmentation Texture feature extraction High order edge-detector 

Notes

Acknowledgements

This work is supported by National Natural Science Foundation of China (NSFC) (61501260, 61471201, 61471203), Jiangsu Province Higher Education Institutions Natural Science Research Key Grant Project (13KJA510004), The peak of six talents in Jiangsu (RLD201402), and “1311 Talent Program” of NJUPT.

References

  1. 1.
    Chan, T., Vese, L.: Active contours without edges. IEEE Trans. Image Process. 10(2), 266–277 (2001)CrossRefGoogle Scholar
  2. 2.
    Li, C., Kao, C., John, C., Ding, Z.: Minimization of region-scalable fitting energy for image segmentation. IEEE Trans. Image Process. 17(10), 1940–1949 (2008)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Zhang, K., Song, H., Zhang, L.: Active contours driven by local image fitting energy. Pattern Recogn. 43(4), 1199–1206 (2010)CrossRefGoogle Scholar
  4. 4.
    Wang, L., He, L., Mishra, A., Li, C.: Active contours driven by local Gaussian distribution fitting energy. Sign. Process. 89(12), 2435–2447 (2009)CrossRefGoogle Scholar
  5. 5.
    Li, C., Huang, R., Ding, Z., Gatenby, J., Metaxas, D., Gore, J.: A level set method for image segmentation in the presence of intensity inhomogeneities with application to MRI. IEEE Trans. Image Process. 20(7), 2007–2016 (2011)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Zhang, K., Zhang, L., Lam, K., Zhang, D.: A level set approach to image segmentation with intensity inhomogeneity. IEEE Trans. Cybern. 46(2), 546–557 (2016)CrossRefGoogle Scholar
  7. 7.
    Min, H., Zhao, Y., Zuo, W., Ling, H., Luo, Y.: LATE: a level-set method based on local approximation of Taylor expansion for segmenting intensity inhomogeneous image. IEEE Trans. Image Process. 27(10), 5016–5031 (2018)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Liu, J., Wei, X., Li, Q., Li, L.: A level set algorithm based on probabilistic statistics for MR image segmentation. In: International Conference on Intelligence Science and Big Data Engineering (IScIDE), pp. 577–586 (2018)Google Scholar
  9. 9.
    Wang, X., Huang, D., Xu, H.: An efficient local Chan-Vese model for image segmentation. Pattern Recogn. 43(3), 603–618 (2010)CrossRefGoogle Scholar
  10. 10.
    Wang, B., Gao, X., Tao, D., Li, X.: A unified tensor level set for image segmentation. IEEE Trans. Syst. Man Cybern.-Part B: Cybern. 40(3), 857–867 (2010)Google Scholar
  11. 11.
    Dai, L., Ding, J., Yang, J.: Inhomogeneity-embedded active contour for natural image segmentation. Pattern Recogn. 48(8), 2513–2529 (2015)CrossRefGoogle Scholar
  12. 12.
    Min, H., Lu, J., Jia, W., Zhao, Y., Luo, Y.: An effective local regional model based on salient fitting for image segmentation. Neurocomputing 311(15), 245–259 (2018)CrossRefGoogle Scholar
  13. 13.
    Kim, W., Kim, C.: Active contours driven by the salient edge energy model. IEEE Trans. Image Process. 22(4), 1667–1673 (2013)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Getreuer, P.: Chan-Vese segmentation. Image Process. Line 2, 214–224 (2012)CrossRefGoogle Scholar
  15. 15.
    Seo, H., Milanfar, P.: Static and space-time visual saliency detection by self-resemblance. J. Vis. 9(12), 1–27 (2009)CrossRefGoogle Scholar
  16. 16.
    Achanta, R., Hemami, S., Estrada, F.: Frequency-tuned saliency region detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1597–1604 (2009)Google Scholar
  17. 17.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Image Processing and Image Communication LabNanjing University of Posts and TelecommunicationsNanjingChina

Personalised recommendations