DIEDA: discriminative information based on exponential discriminant analysis combined with local features representation for face and kinship verification

  • Rachid AliradiEmail author
  • Abdelkader Belkhir
  • Abdelmalik Ouamane
  • Adel S. Elmaghraby


Face and kinship verification using facial images is a novel and challenging problem in computer vision. In this paper, we propose a new system that uses discriminative information, which is based on the exponential discriminant analysis (DIEDA) combined with multiple scale descriptors. The histograms of different patches are concatenated to form a high dimensional feature vector, which represents a specific descriptor at a given scale. The projected histograms for each zone use the cosine similarity metric to reduce the feature vector dimensionality. Lastly, zone scores corresponding to various descriptors at different scales are fused and verified by using a classifier. This paper exploits discriminative side information for face and kinship verification in the wild (image pairs are from the same person or not). To tackle this problem, we take examples of the face samples with unlabeled kin relations from the labeled face in the wild dataset as the reference set. We create an optimized function by minimizing the interclass samples (with a kin relation) and maximizing the neighboring interclass samples (without a kinship relation) with the DIEDA approach. Experimental results on three publicly available face and kinship datasets show the superior performance of the proposed system over other state-of-the-art techniques.


Face and kinship verification Exponential discriminant analysis Multiple scale descriptors Dimensionality reduction Cosine similarity metric 



This work was supported by the research grant from the Ministry of research and higher education (CERIST) of Algeria under Grant PNE number 40 and University of Louisville.


  1. 1.
    Ahonen T, Hadid A, Pietikainen M (2006) Face description with local binary patterns: application to face recognition. IEEE Trans Pattern Anal Mach Intell 28 (12):2037–2041CrossRefzbMATHGoogle Scholar
  2. 2.
    Aliradi R, Bouzera N, Meziane A, Belkhir A (2013) Detection of facial components based on SVM classification and invariant feature. In: Proceeding WI and IAT, V3. IEEE/WIC/ACM, pp 30–36Google Scholar
  3. 3.
    Alvergne A, Oda R, Faurie C, Matsumoto-Oda A, Durand V, Raymond M (2009) Cross-cultural perceptions of facial resemblance between kin. J Vis 9(6):1–10CrossRefGoogle Scholar
  4. 4.
    Chen X, An L, Yang S, Wu W (2017) Kinship verification in multi-linear coherent spaces. Multimedia Tools and Applications 76(22):4105–4122CrossRefGoogle Scholar
  5. 5.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of the CVPR, pp 886–893Google Scholar
  6. 6.
    Deng W, Hu J, Lu J, Guo J (2014) Transform-invariant PCA: a unified approach to fully automatic face alignment, representation, and recognition. IEEE Trans Pattern Anal Mach Intell 36(6):1275–1284CrossRefGoogle Scholar
  7. 7.
    Dibekli Glu H, Salah A-A, Gever T (2013) Like father, like son: Facial expression dynamics for kinship verification. In: Proceedings ICCV, pp 1497–1504Google Scholar
  8. 8.
    Fang R, Tang K, Snavely N, Chen T (2014) Towards computational models of kinship verification. In: Proceedings CIP.IEEE, pp 1577–1580Google Scholar
  9. 9.
    Guo G-D, Wang X (2012) Kinship measurement on salient facial features. IEEE Trans Instrum Meas 1(61):2322–2325CrossRefGoogle Scholar
  10. 10.
    Guo D-H, Yuan Hao H, Van Der-Maaten L (2014) Graph-based kinship recognition. In: Proceedings ICPR, pp 4287–4292Google Scholar
  11. 11.
    Hu H (2008) Orthogonal neighborhood preserving discriminant analysis for face recognition. Pattern Recogn 41(6):2045–2054CrossRefzbMATHGoogle Scholar
  12. 12.
    Huang GB, Ramesh M, Berg T, Learned-Miller E (2007) Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Dept. Computer Science, University of Massachusetts, Amherst, pp 07–49Google Scholar
  13. 13.
    Jiang X (2011) Linear subspace learning-based dimensionality reduction. IEEE Signal Proc Mag 28(2):16–26CrossRefGoogle Scholar
  14. 14.
    Kan M, Xu D, Shan S, Li W, Chen X (2013) Learning prototype hyperplanes for face verification in the wild. IEEE Trans Image Process 22(8):3310–3316CrossRefGoogle Scholar
  15. 15.
    Kannala J, Rahtu E (2012) BSIF: Binarized statistical image features. In: Proceedings IEEE Conf. ICPR, pp 1363–1366Google Scholar
  16. 16.
    Kannala J, Rahtu E (2012) BSIF binarized statistical image features. In: Proceedings ICPR. IEEE, Piscataway, pp 1363–1366Google Scholar
  17. 17.
    Kohli N, Singh R, Vatsa M (2012) Self-similarity representation of weber faces for kinship classification. In: Proceedings ICBTAAS. IEEE, Piscataway, pp 245–250Google Scholar
  18. 18.
    Le Q-V, Zou W-Y, Yeung S-Y, Ng A-Y (2011) Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In: Proceedings. CPVR, IEEE, pp 3361– 3368Google Scholar
  19. 19.
    Li Z, Lin D, Tang X (2009) Non parametric discriminant analysis for face recognition. IEEE Trans Pattern Anal Mach Intell 31(4):755–761CrossRefGoogle Scholar
  20. 20.
    Liu C (2014) Discriminant analysis and similarity measure. Pattern Recogn 1 (47):359–367CrossRefGoogle Scholar
  21. 21.
    Liu C, Wechsler H (2002) Gabor feature based classification using the enhanced Fisher linear discriminant model for face recognition. IEEE Trans Image Process 11 (4):467–476CrossRefGoogle Scholar
  22. 22.
    Lopez M-B, Boutellaa E, Hadid A (2016) Comments on the kinship face in the wild data sets. IEEE Trans Pattern Anal Mach Intell 27:2342–2344Google Scholar
  23. 23.
    Lu J, Zhou X, Tan Y-P, Shang Y, Zhou J (2014) Neighborhood repulsed metric learning for kinship verification. IEEE Trans Pattern Anal Mach Intell 36(2):331–345CrossRefGoogle Scholar
  24. 24.
    Lu J, Hu J, Liong V-E, Zhou X, Bottino A, Islam I-U, Vieira T-F, Qin X, Tan X, Keller Y (2015) In: 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), vol. 02. 1–6Google Scholar
  25. 25.
    Lu J, Liang V-E, Zhou X, Zhou J (2015) Learning compact binary face descriptor for face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (Code is available by request)Google Scholar
  26. 26.
    Meina K, Kan S, Shan DX, Chen X (2011) Side-information based linear discriminant analysis for face recognition. In: British machine vision conference, pp 125.0–125.1Google Scholar
  27. 27.
    Meyer CD (2000) Matrix analysis and applied linear algebra, published by SIAMGoogle Scholar
  28. 28.
    Minka T-P (2003) A comparison of numerical optimizers for logistic Regression (Technical Report 758). Carnegie Mellon University, Department of StatisticsGoogle Scholar
  29. 29.
    Mohammed A, Siti Zaiton Mohd H, Dzulkifli M, AM Hazim A-M, Aida A (2017) Automated kinship verification and identification through human facial images: A Survey. Multimedia Tools and Applications 1(76):265–307Google Scholar
  30. 30.
    Isa M-R-M, Aljareh S, Yusoff Z (2017) A watermarking technique to improve the security level in face recognition systems. Multimedia Tools and Applications 76 (22):23805–23830CrossRefGoogle Scholar
  31. 31.
    Rekers J , Schürr A (1997) Defining and parsing visual languages with layered graph grammars. J Vis Lang Comput Elsevier (8):27–55Google Scholar
  32. 32.
    Somanath G, Kambhamettu C (2012) Can faces verify blood relations? . In: Proceedins IEEE international conference on biometrics: theory, applications and systems, pp 105–112Google Scholar
  33. 33.
    Taigman Y, Wolf L, Taigman Y (2009) Multiple one-shots for utilizing class label information. In: British machine vision conference, BMVCGoogle Scholar
  34. 34.
    Turk M, Pentland A (1991) Eigenfaces for recognition. J Cogn Neurosci, MIT Press 3(1):71–86CrossRefGoogle Scholar
  35. 35.
    Wolf L, Hassner T, Taigman Y (2008) Descriptor Based Methods in the Wild. In: Proceedings workshop on faces in ‘Real-Life’ images: detection, alignment and recognition, CSCV, pp 1–14Google Scholar
  36. 36.
    Wolf L, Hassner T, Taigman Y (2011) Effective face recognition by combining multiple descriptors and learned background statistics. IEEE Trans Pattern Anal Mach Intell 33(10):1978–1990CrossRefGoogle Scholar
  37. 37.
    Xia S, Shao M, Fu Y (2011) Kinship verification through transfer learning. In: IJCAI, pp 2539–2544Google Scholar
  38. 38.
    Xia S, Shao M, Luo J, Fu Y (2012) Understanding kin relationships in a photo. IEEE Trans Multimedia 14(4):1046–1056CrossRefGoogle Scholar
  39. 39.
    Xing E-P, Ng A-Y, Jordan M-I, Russell S (2002) Distance metric learning, with application to clustering with side-information. In: Advances in neural information processing systemsGoogle Scholar
  40. 40.
    Yan H, Lu J, Deng W, Zhou X (2015) Discriminative multi-metric learning for kinship verification. IEEE Trans Inf Forensics Secur 9(7):1169–1178CrossRefGoogle Scholar
  41. 41.
    Yan H, Lu J, Zhou X (2015) Prototype-based discriminative feature learning for kinship verification. IEEE Transactions on Cybernetics 45(11):2535–2545CrossRefGoogle Scholar
  42. 42.
    Yu W, Teng X, Liu C (2006) Face recognition using discriminant locality preserving projections. Image Vis Comput 24(3):239–248CrossRefGoogle Scholar
  43. 43.
    Zhang T, Fang B, Tang Y-Y, Shang Z-W, Xu B (2010) Generalized discriminant analysis: a matrix exponential approach. IEEE Trans Pattern Anal Mach Intell 40(1):186–197Google Scholar
  44. 44.
    Zhou X, Hu J, Lu J, Shang Y, Guan Y (2011) Kinship verification from facial images under uncontrolled conditions. In: Proceedings ACM multimedia. ACM, New York, pp 953–956Google Scholar
  45. 45.
    Zhou X, Lu J, Hu J, Shang Y (2012) Gabor-based gradient orientation pyramid for kinship verification under uncontrolled environments. In: Proceedings ACM multimedia. ACM, New York, pp 725–728Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computer Engineering, Computer ScienceUniversity of LouisvilleLouisvilleUSA
  2. 2.University of Sciences and Technology (USTHB) and CERISTAlgiersAlgeria
  3. 3.Department of Electrical EngineeringUniversity of Mohamed KhiderBiskraAlgeria

Personalised recommendations