Metric Learning for Facial Kinship Verification

  • Haibin YanEmail author
  • Jiwen Lu
Part of the SpringerBriefs in Computer Science book series (BRIEFSCOMPUTER)


In this chapter, we discuss metric learning techniques for facial kinship verification. We first review several conventional and representative metric learning methods, including principal component analysis (PCA), linear discriminant analysis (LDA), locality preserving projections (LPP), information-theoretic metric learning (ITML), side-information-based linear discriminant analysis (SILD), KISS metric learning (KISSME), and cosine similarity metric learning (CSML) for face similarity measure. Then, we introduce a neighborhood repulsed correlation metric learning (NRCML) method for facial kinship verification. Most existing metric learning-based kinship verification methods are developed with the Euclidian similarity metric, so that they are not powerful enough to measure the similarity of face samples. Since face images are usually captured in wild conditions, our NRCML method uses the correlation similarity measure, where the kin relation of facial images can be better highlighted. Moreover, since negative kinship samples are usually less than positive samples, the NRCML method automatically identifies the most discriminative negative samples in the training set to learn the distance metric so that the most discriminative encoded by negative samples can better exploited. Next, we introduce a discriminative multi-metric learning (DMML) method for kinship verification. This method makes use of multiple face descriptors, so that complementary and discriminative information is exploited for verification.


Linear Discriminant Analysis Face Image Near Neighbor Feature Representation Locality Preserve Projection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. fisherfaces: recognition using class specific linear projection. IEEE Trans. Pattern Analy. Mach. Intell. 19(7), 711–720 (1997)CrossRefGoogle Scholar
  2. 2.
    Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput. 15(6), 1373–1396 (2003)CrossRefzbMATHGoogle Scholar
  3. 3.
    Beveridge, J.R., She, K., Draper, B., Givens, G.H.: Parametric and nonparametric methods for the statistical evaluation of human id algorithms. In: IEEE Third Workshop on Empirical Evaluation Methods in Computer Vision, pp. 2919–2924 (2001)Google Scholar
  4. 4.
    Cinbis, R., Verbeek, J., Schmid, C.: Unsupervised metric learning for face identification in TV video. In: IEEE Interntaional Conference on Computer Vision, pp. 1559–1566 (2011)Google Scholar
  5. 5.
    Davis, J., Kulis, B., Jain, P., Sra, S., Dhillon, I.: Information-theoretic metric learning. In: International Conference on Machine Learning, pp. 209–216 (2007)Google Scholar
  6. 6.
    Goldberger, J., Roweis, S., Hinton, G., Salakhutdinov, R.: Neighborhood component analysis. In: Advances in Neural Information Processing Systems, pp. 2539–2544 (2004)Google Scholar
  7. 7.
    Guillaumin, M., Verbeek, J., Schmid, C.: Is that you? Metric learning approaches for face identification. In: International Conference on Computer Vision, pp. 498–505 (2009)Google Scholar
  8. 8.
    He, X., Yan, S., Hu, Y., Niyogi, P., Zhang, H.J.: Face recognition using laplacianfaces. IEEE Trans. Pattern Anal. Mach. Intell. 27(3), 328–340 (2005)CrossRefGoogle Scholar
  9. 9.
    Kan, M., Shan, S., Xu, D., Chen, X.: Side-information based linear discriminant analysis for face recognition. In: British Machine Vision Conference, vol. 11, pp. 125–1. Citeseer (2011)Google Scholar
  10. 10.
    Kostinger, M., Hirzer, M., Wohlhart, P., Roth, P., Bischof, H.: Large scale metric learning from equivalence constraints. In: IEEE International Conference Computer Vision and Pattern Recognition, pp. 2288–2295 (2012)Google Scholar
  11. 11.
    Liong, V.E., Lu, J., Wang, G., Moulin, P., Zhou, J.: Deep hashing for compact binary codes learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2475–2483 (2015)Google Scholar
  12. 12.
    Lu, J., Tan, Y.P., Wang, G.: Discriminative multimanifold analysis for face recognition from a single training sample per person. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 39–51 (2013)CrossRefGoogle Scholar
  13. 13.
    Lu, J., Wang, G., Moulin, P.: Human identity and gender recognition from gait sequences with arbitrary walking directions. IEEE Trans. Inf. Forensics Secur. 9(1), 51–61 (2014)CrossRefGoogle Scholar
  14. 14.
    Lu, J., Zhang, E.: Gait recognition for human identification based on ICA and fuzzy SVM through multiple views fusion. Pattern Recognit. Lett. 28(16), 2401–2411 (2007)CrossRefGoogle Scholar
  15. 15.
    Lu, J., Zhou, X., Tan, Y.P., Shang, Y., Zhou, J.: Neighborhood repulsed metric learning for kinship verification. IEEE Trans. Pattern Anal. Mach. Intell. 34(2), 331–345 (2014)Google Scholar
  16. 16.
    Mignon, A., Jurie, F.: PCCA: a new approach for distance learning from sparse pairwise constraints. In: IEEE International Conference Computer Vision and Pattern Recognition, pp. 2666–2672 (2012)Google Scholar
  17. 17.
    Mu, Y., Ding, W., Tao, D.: Local discriminative distance metrics ensemble learning. Pattern Recognit. 46, 2337–2349 (2013)CrossRefzbMATHGoogle Scholar
  18. 18.
    Nguyen, H., Bai, L.: Cosine similarity metric learning for face verification. In: Asian Conference on Computer Vision, pp. 709–720 (2010)Google Scholar
  19. 19.
    Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)CrossRefGoogle Scholar
  20. 20.
    Schiffman, S., Reynolds, M., Young, F., Carroll, J.: Introduction to Multidimensional Scaling: Theory, Methods, and Applications. Academic Press, New York (1981)zbMATHGoogle Scholar
  21. 21.
    Sharma, A., Kumar, A., Daume III, H., Jacobs, D.: Generalized multiview analysis: a discriminative latent space. In: IEEE International Conference Computer Vision and Pattern Recognition, pp. 1867–1875 (2012)Google Scholar
  22. 22.
    Tran, D., Sorokin, A.: Human activity recognition with metric learning. In: European Conference on Computer Vision, pp. 548–561 (2008)Google Scholar
  23. 23.
    Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cogn. Neurosci. 3(1), 71–86 (1991)CrossRefGoogle Scholar
  24. 24.
    Weinberger, K., Blitzer, J., Saul, L.: Distance metric learning for large margin nearest neighbor classification. In: Advances in Neural Information Processing Systems (2005)Google Scholar
  25. 25.
    Xiao, B., Yang, X., Xu, Y., Zha, H.: Learning distance metric for regression by semidefinite programming with application to human age estimation. In: ACM International Conference on Multimedia, pp. 451–460 (2009)Google Scholar
  26. 26.
    Xing, E., Ng, A., Jordan, M., Russell, S.: Distance metric learning, with application to clustering with side-information. In: Advances in Neural Information Processing Systems, pp. 505–512 (2002)Google Scholar
  27. 27.
    Yan, H.: Kinship verification using neighborhood repulsed correlation metric learning. Image and Vision Computing (2017)Google Scholar
  28. 28.
    Yan, H., Lu, J., Deng, W., Zhou, X.: Discriminative multimetric learning for kinship verification. IEEE Trans. Inf. Forensics Secur. 9(7), 1169–1178 (2014)CrossRefGoogle Scholar
  29. 29.
    Zheng, W., Gong, S., Xiang, T.: Person re-identification by probabilistic relative distance comparison. In: IEEE International Conference Computer Vision and Pattern Recognition, pp. 649–656 (2011)Google Scholar

Copyright information

© The Author(s) 2017

Authors and Affiliations

  1. 1.Beijing University of Posts and TelecommunicationsBeijingChina
  2. 2.Tsinghua UniversityBeijingChina

Personalised recommendations