Face segmentation based on level set and improved DBM prior shape

  • Xiaoling Wu
  • Ji ZhaoEmail author
  • Huibin Wang
Regular Paper


This paper puts forward a new method of level set image segmentation based on prior shape, which aims to provide a better solution to the challenging segmentation problems that typically occur in images with complex background, intensity inhomogeneity and partially blocked targets. First, we introduced glial cells into deep Boltzmann machine (DBM) to solve that units in the DBM layer are not connected to each other, and then the novel DBM is employed to learn prior shape. Next, we used the variational level set and the local Gaussian distribution to fit the image energy term with local mean and local variance of image. Then, the prior shape energy is integrated into the image energy term to construct the final energy segmentation model. The experimental results show that the new model has stronger robustness and higher efficiency for face images segmentation.


Face segmentation Improved DBM Level set Prior shape 



This Research is funded by the Education Department of Liaoning Province Foundation Grant Number LJQ2014033 and the Natural Science Foundation of Liaoning Province Grant Number 20180551048.


  1. 1.
    Li, Y., Wang, S., Li, C.: A fast color image segmentation approach using GDF with improved region-level Ncut. Math. Probl. Eng. 3, 1–14 (2018)Google Scholar
  2. 2.
    Buenestado, P., Acho, L.: Image segmentation based on statistical confidence intervals. Entropy 20(46), 1–12 (2018)Google Scholar
  3. 3.
    Li, P., Li, Z.: Color image segmentation using PSO-based histogram thresholding. WIT Trans. Inf. Commun. Technol. 52, 1601–1607 (2014)Google Scholar
  4. 4.
    Hassanat, A., Alkasassbeh, M., Al-Awadi, M.: Color-based object segmentation method using artificial neural network. Simul. Model. Pract. Theory 64, 3–17 (2016)Google Scholar
  5. 5.
    Zhao, Y., Tang, F., Dong, W.: Joint face alignment and segmentation via deep multi-task learning. Multimed. Tools Appl. 8, 1–18 (2018)Google Scholar
  6. 6.
    Ravishankar, H., Thiruvenkadam, S., Venkataramani, R.: Joint deep learning of foreground, background and shape for robust contextual segmentation, pp. 622–632 (2017)Google Scholar
  7. 7.
    Filipe, S., Alexandre, L.A.: Algorithms for invariant long-wave infrared face segmentation: evaluation and comparison. Pattern Anal. Appl. 17(4), 823–837 (2014)MathSciNetGoogle Scholar
  8. 8.
    Nidhal, K., Abbadi, E., Abdul, A.: Detection and segmentation of human face. Int. J. Adv. Res. Comput. Commun. Eng. 4(2), 90–94 (2015)Google Scholar
  9. 9.
    Cheddad, A., Mohamad, D., Manaf, A.A.: Exploiting Voronoi diagram properties in face segmentation and feature extraction. Pattern Recognit. 41(12), 3842–3859 (2008)zbMATHGoogle Scholar
  10. 10.
    Adipranata, R., Ballangan, C.G., Ongkodjojo, R.P.: Fast method for multiple human face segmentation in color image. In: International Conference on Future Generation Communication and Networking, vol. 3, no. 2, pp. 158–161. IEEE Computer Society (2008)Google Scholar
  11. 11.
    Kamencay, P., Zachariasova, M., Hudec, R.: A novel approach to face recognition using image segmentation based on SPCA-KNN method. Radioengineering 22(1), 92–99 (2013)Google Scholar
  12. 12.
    Kawulok, M., Celebi, M.E., Smolka, B.: Advances in face detection and facial image analysis. Springer 4(6), 561–567 (2016)Google Scholar
  13. 13.
    Filipe, S., Alexandre, L.A.: Improving face segmentation in thermograms using image signatures. In: Iberoamerican Congress Conference on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, pp. 402–409. Springer (2010)Google Scholar
  14. 14.
    Filipe, S., Alexandre, L.A.: Thermal infrared face segmentation: a new pose invariant method. Lect. Notes Comput. Sci. 7887, 632–639 (2013)Google Scholar
  15. 15.
    Samir, K.B.: A method for face segmentation, facial feature extraction and tracking. Int. J. Comput. Sci. Eng. Technol. 1(3), 137–139 (2014)Google Scholar
  16. 16.
    Kumaravel, M., Karthik, S., Sivraj, P.P.: Human face image segmentation using level set methodology. Int. J. Comput. Appl. 44(12), 0975–8887 (2012)Google Scholar
  17. 17.
    Jing-Feng, M.A., Liu, Y., Xin, Q.I.: A cell image segmentation method based on single level set function. Chin. J. Med. Phys. 30(6), 4522–4523 (2013)Google Scholar
  18. 18.
    Tan, H., Jiang, H., Dong, A.: C–V level set based cell image segmentation using color filter and morphology. In: International Conference on Information Science, Electronics and Electrical Engineering, vol. 2, pp. 1073–1077. IEEE (2014)Google Scholar
  19. 19.
    Zhang, R., Zhu, S., Zhou, Q.: A novel gradient vector flow snake model based on convex function for infrared image segmentation. Sensors 16(10), 1–7 (2016)Google Scholar
  20. 20.
    Lim, P.H., Bagci, U., Bai, L.: A new prior shape model for level set segmentation. In: Iberoamerican Congress on Pattern Recognition, vol. 7042, pp. 125–132. Springer, Berlin (2011)Google Scholar
  21. 21.
    Qiao, Y., Wei, Z., Zhao, Y.: Thermal infrared pedestrian image segmentation using level set method. Sensors 17(8), 1811 (2017)Google Scholar
  22. 22.
    Ma, Q., Kong, D.: A new variational model for joint restoration and segmentation based on the Mumford–Shah model. J. Vis. Commun. Image Represent. 53, 224–234 (2018)Google Scholar
  23. 23.
    Li, C., Kao, C.Y., Gore, J.C., Ding, Z.: Implicit active contours driven by local binary fitting energy. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR ’07, vol. 2007, no. 1, pp. 1–7. IEEE (2007)Google Scholar
  24. 24.
    Leventon, M.E., Grimson, W.E.L., Faugeras, O.: Statistical shape influence in geodesic active contours. In: IEEE EMBS International Summer School on Biomedical Imaging, vol. 1, p. 8. IEEE (2003)Google Scholar
  25. 25.
    Rousson., M, Paragios., N.: Shape priors for level set representations. In: European Conference on Computer Vision, vol. 2351, pp. 78–92 (2002)Google Scholar
  26. 26.
    Khalifa, F., Elbaz, A., Gimel’Farb, G.: Shape-appearance guided level-set deformable model for image segmentation. In: International Conference on Pattern Recognition, pp. 4581–4584. IEEE (2010)Google Scholar
  27. 27.
    Majeed, T., Fundana, K., Kiriyanthan, S.: Graph cut segmentation using a constrained statistical model with non-linear and sparse shape optimization. In: Medical Computer Vision, Recognition Techniques and Applications in Medical Imaging, vol. 7766, pp. 48–58. Springer, Berlin (2012)Google Scholar
  28. 28.
    Salakhutdinov, R., Hinton, G.: Deep Boltzmann machines. J. Mach. Learn. Res. 5(2), 1967–2006 (2009)zbMATHGoogle Scholar
  29. 29.
    Salakhutdinov, R., Hinton, G.: An efficient learning procedure for deep Boltzmann machines. Neural Comput. 24(8), 1967–2006 (2014)MathSciNetzbMATHGoogle Scholar
  30. 30.
    Kai, Y., Lei, J., Chen, Y.: Deep learning: yesterday, today, and tomorrow. J. Comput. Res. Dev. 50(9), 1799–1804 (2013)Google Scholar
  31. 31.
    Cheng, F., Zhang, H., Fan, Wl: Image recognition technology based on deep learning. Wirel. Pers. Commun. 102(2), 1–17 (2018)Google Scholar
  32. 32.
    Karahan, S., Akgul, Y.S.: Eye detection by using deep learning. In: Signal Processing and Communication Application Conference, pp. 2145–2148. IEEE (2016)Google Scholar
  33. 33.
    Zhou, S., Chen, Q., Wang, X.: Active deep learning method for semi-supervised sentiment classification. Neurocomputing 120(10), 536–546 (2013)Google Scholar
  34. 34.
    Chen, C.L.P., Zhang, C.Y., Chen, L.: Fuzzy restricted Boltzmann machine for the enhancement of deep learning. IEEE Trans. Fuzzy Syst. 23(6), 2163–2173 (2015)Google Scholar
  35. 35.
    Chen, Y.: Mineral potential mapping with a restricted Boltzmann machine. Ore Geol. Rev. 71, 749–760 (2015)Google Scholar
  36. 36.
    Odense, S., Edwards, R.: Universal approximation results for the temporal restricted Boltzmann Machine and the recurrent temporal restricted Boltzmann Machine. J. Mach. Learn. Res. 17, 1–21 (2016)MathSciNetzbMATHGoogle Scholar
  37. 37.
    Cai, X., Hu, S., Lin, X.: Feature extraction using restricted Boltzmann machine for stock price prediction. In: IEEE International Conference on Computer Science and Automation Engineering, vol. 3, pp. 80–83. IEEE (2012)Google Scholar
  38. 38.
    Cho, K.H., Raiko, T., Ilin, A.: Gaussian–Bernoulli deep Boltzmann machine. In: International Joint Conference on Neural Networks, pp. 1–7. IEEE (2013)Google Scholar
  39. 39.
    Srivastava, N., Salakhutdinov, R.: Multimodal learning with deep Boltzmann machines. In: International Conference on Neural Information Processing Systems, vol. 15, pp. 2222–2230 (2012)Google Scholar
  40. 40.
    He, S., Wang, S., Lan, W., Fu, H., Ji, Q.: Facial expression recognition using deep Boltzmann machine from thermal infrared images. Affect. Comput. Intell. Interact. 7971, 239–244 (2013)Google Scholar
  41. 41.
    Wang, L., He, L., Mishra, A.: Active contours driven by local Gaussian distribution fitting energy. Signal Process. 89(12), 2435–2447 (2009)zbMATHGoogle Scholar
  42. 42.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, vol. 1, pp. 511–518. IEEE (2003)Google Scholar
  43. 43.
    Liu, N., Zhai, G.: Free energy adjusted peak signal to noise ratio (FEA-PSNR) for image quality assessment. Sens. Imaging 18(1), 11 (2017)Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Software EngineeringUniversity of Science and Technology LiaoningAnshanChina

Personalised recommendations