Skip to main content
SpringerLink
Log in

A survey of virtual sample generation technology for face recognition

  • Published:
Artificial Intelligence Review Aims and scope Submit manuscript

Abstract

Despite considerable advances made in face recognition in recent years, the recognition performance still suffers from insufficient training samples. Hence, various algorithms have been proposed for addressing the problems of small sample size with dramatic variations in illuminations, poses and facial expressions in face recognition. Among these algorithms, the virtual sample generation technology achieves promising performance with reasonable and effective mathematical function and easy implementation. In this paper, we systematically summarize the research progress in the virtual sample generation technology for face recognition and categorize the existing methods into three groups, namely, (1) construction of virtual face images based on the face structure; (2) construction of virtual face images based on the idea of perturbation and distribution function of samples; (3) construction of virtual face images based on the sample viewpoint. We carry out thorough and comprehensive comparative study in which different methods are compared by conducting an in-depth analysis on them. It demonstrates the significant advantage of combining the virtual sample generation technology with representation based methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  • Beymer D, Poggio T (1995) Face recognition from one example view. In: International conference on computer vision. IEEE Computer Society, p 500

  • Chen X, Yang J, Zhang D et al (2013) Complete large margin linear discriminant analysis using mathematical programming approach. Pattern Recognit 46(6):1579–1594

    Article  MATH  Google Scholar 

  • Ding F (2010) Several multi-innovation identification methods. Digit Signal Process 20(4):1027–1039

    Article  MathSciNet  Google Scholar 

  • Fan Z, Xu Y, Zhang D (2011) Local linear discriminant analysis framework using sample neighbors. IEEE Trans Neural Netw 22(7):1119–1132

    Article  Google Scholar 

  • Gao W, Shan S, Chai X et al (2003) Virtual face image generation for illumination and pose insensitive face recognition. In: Proceedings of the international conference on multimedia and expo, pp 149–152

  • Gu G, Hou Z, Chen C et al (2016) A dimensionality reduction method based on structured sparse representation for face recognition. Artif Intell Rev 46(4):1–13

    Article  Google Scholar 

  • Harguess J, Aggarwal JK (2011) Is there a connection between face symmetry and face recognition? In: IEEE workshops (CVPR 2011), pp 66–73

  • Harguess J, Gupta S, Aggarwal J K (2008) 3D face recognition with the average-half-face. In: 19th international conference on pattern recognition (ICPR 2008). IEEE, pp 1–4

  • He X, Yan S, Hu Y et al (2005) Face recognition using Laplacianfaces. IEEE Trans Pattern Anal Mach Intell 27(3):328–340

    Article  Google Scholar 

  • Hu Y, Jiang D, Yan S, et al (2004) Automatic 3D reconstruction for face recognition. In: Proceedings of the sixth IEEE international conference on automatic face and gesture recognition. IEEE, pp 843–848

  • Isenor DK, Zaky SG (1986) Fingerprint identification using graph matching. Pattern Recognit 19(2):113–122

    Article  Google Scholar 

  • Jiang Z, Lin Z, Davis LS (2013) Label consistent K-SVD: learning a discriminative dictionary for recognition. IEEE Trans Pattern Anal Mach Intell 35(35):2651–2664

    Article  Google Scholar 

  • Jung H C, Hwang B W, Lee S W (2004) Authenticating corrupted face image based on noise model. In: Proceedings of the sixth IEEE international conference on automatic face and gesture recognition. IEEE, pp 272–277

  • Jun B, Kim D (2012) Robust face detection using local gradient patterns and evidence accumulation. Pattern Recognit 45(9):3304–3316

    Article  Google Scholar 

  • Kautkar SN, Atkinson GA, Smith ML (2012) Face recognition in 2D and 2.5D using ridgelets and photometric stereo. Pattern Recognit 45(9):3317–3327

    Article  Google Scholar 

  • Kim SW (2006) On using a dissimilarity representation method to solve the small sample size problem for face recognition. In: International conference on advanced concepts for intelligent vision systems. Springer, Heidelberg, pp 1174–1185

  • Kirby M, Sirovich L (1990) Application of the Karhunen–Loeve procedure for the characterization of human faces. IEEE Trans Pattern Anal Mach Intell 12(1):103–108

    Article  Google Scholar 

  • Kusakari T, Wakiyama K (2003) Iris identification apparatus and iris image pickup apparatus. U.S. Patent Application 10/195,342[P]. 2002-7-15

  • Kyperountas M, Tefas A, Pitas I (2007) Weighted piecewise LDA for solving the small sample size problem in face verification. IEEE Trans Neural Netw 18(2):506–519

    Article  Google Scholar 

  • Leyton Michael (1992) Symmetry, causality, mind. MIT Press, Cambridge

    Google Scholar 

  • Li Z, Lai Z, Xu Y et al (2015) A locality-constrained and label embedding dictionary learning algorithm for image classification. IEEE Trans Neural Netw Learn Syst 1–16

  • Li L, Liu S, Peng Y et al (2016) Overview of principal component analysis algorithm. Optik Int J Light Electron Opt 127(9):3935–3944

    Article  Google Scholar 

  • Liu YH, Chen YT (2007) Face recognition using total margin-based adaptive fuzzy support vector machines. IEEE Trans Neural Netw 18(1):178–192

    Article  Google Scholar 

  • Liu J, Chen S, Zhou ZH et al (2007) Single image subspace for face recognition. In: International conference on analysis and modeling of faces and gestures. Springer, Berlin, pp 205–219

  • Liu Z, Pu J, Wu Q et al (2015a) Using the original and symmetrical face training samples to perform collaborative representation for face recognition. Optik Int J Light Electron Opt 127(4):1900–1904

    Article  Google Scholar 

  • Liu Z, Song X, Tang Z (2015b) Fusing hierarchical multi-scale local binary patterns and virtual mirror samples to perform face recognition. Neural Comput Appl 26(8):2013–2026

    Article  Google Scholar 

  • Lu J, Yuan X, Yahagi T (2007) A method of face recognition based on fuzzy c-means clustering and associated sub-NNs. IEEE Trans Neural Netw 18(1):150–160

    Article  Google Scholar 

  • Neves J, Narducci F, Barra S et al (2016) Biometric recognition in surveillance scenarios: a survey. Artif Intell Rev 1–27

  • Passalis G, Perakis P, Theoharis T et al (2011) Using facial symmetry to handle pose variations in real-world 3D face recognition. IEEE Trans Pattern Anal Mach Intell 33(10):1938–1951

    Article  Google Scholar 

  • Pishchulin L, Gass T, Dreuw P et al (2012) Image warping for face recognition: from local optimality towards global optimization. Pattern Recognit 45(9):3131–3140

    Article  Google Scholar 

  • Poggio T, Vetter T (1992) Recognition and structure from one 2D model view: observations on prototypes. Object classes and symmetries. Laboratory Massachusetts Institute of Technology, Cambridge, p 1347

  • Royer FL (1981) Detection of symmetry. J Exp Psychol Hum Percept Perform 7(6):1186–1210

    Article  Google Scholar 

  • Ryu Y-S, Oh S-Y (2002) Simple hybrid classifier for face recognition with adaptively generated virtual data. Pattern Recognit Lett 23(7):833–841

    Article  MATH  Google Scholar 

  • Saber E, Tekalp AM (1998) Frontal-view face detection and facial feature extraction using color, shape and symmetry based cost functions. Pattern Recognit Lett 19(8):669–680

    Article  MATH  Google Scholar 

  • Saha S, Bandyopadhyay S (2007) A symmetry based face detection technique. In: Proceedings of the IEEE WIE national symposium on emerging technologies, pp 1–4

  • Shan GJ (2013) Virtual sample generating for face recognition from a single training sample per person. Sci Technol Eng 13(14):3908–3911

    Google Scholar 

  • Sharma A, Dubey A, Tripathi P et al (2010) Pose invariant virtual classifiers from single training image using novel hybrid-eigenfaces. Neurocomputing 73(10–12):1868–1880

    Article  Google Scholar 

  • Smeets D, Keustermans J, Hermans J et al (2011) Symmetric surface-feature based 3D face recognition for partial data. In: International joint conference on biometrics. IEEE Computer Society, pp 1–6

  • Song X, Shao C, Yang X et al (2016) Sparse representation-based classification using generalized weighted extended dictionary. Soft Comput 1–14

  • Su MC, Chou CH (1999) Application of associative memory in human face detection. In: 1999 international joint conference on neural networks, pp 3194–3197

  • Thian NPH, Marcel S, Bengio S (2003) Improving face authentication using virtual samples. In: Proceedings of the IEEE international conference on acoustics, speech, and signal processing (ICASSP ’03), vol 3. IEEE, p III-233-6

  • Vapnik VN (1995) The nature of statistical learning theory. IEEE Trans Neural Netw 10(5):988–999

    Article  MATH  Google Scholar 

  • Vetter T (1998) Synthesis of novel views from a single face image. Int J Comput Vis 28(2):103–116

    Article  Google Scholar 

  • Wang WD, Yang JY (2008) Quadratic discriminant analysis method based on virtual training samples. Acta Autom Sin 34(4):400–407

    Article  MATH  Google Scholar 

  • Wang J, You J, Li Q et al (2012) Orthogonal discriminant vector for face recognition across pose. Pattern Recognit 45(12):4069–4079

    Article  MATH  Google Scholar 

  • Wang Y, Wang M, Chen Y et al (2014) A novel virtual samples-based sparse representation method for face recognition. Optik Int J Light Electron Opt 125(15):3908–3912

    Article  Google Scholar 

  • Wiskott L, Fellous JM, Kuiger N et al (1997) Face recognition by elastic bunch graph matching. IEEE Trans Pattern Anal Mach Intell 19(7):775–779

    Article  Google Scholar 

  • Wright J, Yang AY, Ganesh A et al (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31(2):2368–2378

    Article  Google Scholar 

  • Wu S, Cao J (2014) ‘Symmetrical face’ based improved LPP method for face recognition. Optik Int J Light Electron Opt 125(14):3530–3533

    Article  Google Scholar 

  • Xu Y, Zhang D, Yang J et al (2011) A two-phase test sample sparse representation method for use with face recognition. IEEE Trans Circuits Syst Video Technol 21(9):1255–1262

    Article  MathSciNet  Google Scholar 

  • Xu Y, Zhu Q, Fan Z et al (2013a) Coarse to fine K nearest neighbor classifier. Pattern Recognit Lett 34(9):980–986

    Article  Google Scholar 

  • Xu Y, Zhu X, Li Z et al (2013b) Using the original and ‘symmetrical face’ training samples to perform representation based two-step face recognition. Pattern Recognit 46(4):1151–1158

    Article  Google Scholar 

  • Xu Y, Li X, Yang J et al (2014a) Integrate the original face image and its mirror image for face recognition. Neurocomputing 131(7):191–199

    Article  Google Scholar 

  • Xu Y, Li X, Yang J et al (2014b) Integrating conventional and inverse representation for face recognition. IEEE Trans Cybern 44(10):1738–1746

    Article  Google Scholar 

  • Xu Y, Fang X, Li X et al (2014c) Data uncertainty in face recognition. IEEE Trans Cybern 44(10):1950–1961

    Article  Google Scholar 

  • Xu Y, Fei L, Zhang D (2015a) Combining left and right palmprint images for more accurate personal identification. IEEE Trans Image Process 24(2):549–559

    Article  MathSciNet  Google Scholar 

  • Xu Y, Fang X, You J et al (2015b) Noise-free representation based classification and face recognition experiments. Neurocomputing 147:307–314

    Article  Google Scholar 

  • Xu Y, Zhang B, Zhong Z (2015c) Multiple representations and sparse representation for image classification. Pattern Recognit Lett 68:9–14

    Article  Google Scholar 

  • Xu Y, Zhang Z, Lu G et al (2016) Approximately symmetrical face images for image preprocessing in face recognition and sparse representation based classification. Pattern Recognit 54:68–82

    Article  Google Scholar 

  • Zhai GY (2011) Pose-varied face recognition based on facial pose correction and virtual samples. Comput Simul 28(8):264–267

    Google Scholar 

  • Zhang SL (2006) Various pose face recognition with one front training sample. J Comput Appl 26(12):2851–2853

    Google Scholar 

  • Zhang L, Razdan A, Farin G et al (2006) 3D face authentication and recognition based on bilateral symmetry analysis. Vis Comput 22(1):43–55

    Article  Google Scholar 

  • Zhang D, Song F, Xu Y et al (2008) Advanced pattern recognition technologies with applications to biometrics. Medical Information Science Reference, New York

    Google Scholar 

  • Zhang T, Li X, Guo RZ (2014) Producing virtual face images for single sample face recognition. Optik Int J Light Electron Opt 125(17):5017–5024

    Article  Google Scholar 

  • Zhao W, Chellappa R, Phillips PJ et al (2003) Face recognition: a literature survey. ACM Comput Surv 35(4):399–458

    Article  Google Scholar 

  • Zou C, Sun N, Ji Z, et al (2007) 2DCCA: a novel method for small sample size face recognition. In: IEEE workshop on applications of computer vision. IEEE, p 43

Download references

Acknowledgements

This work is supported by the National Natural Science Foundation of China (Nos. 61402274, 41471280, 61461025, 61501286, 61202314, U1504610), the Pivot Science and Technology Innovation Team of Shaanxi Province of China (No. 2014KTC-18), the Key Science and Technology Program of Shaanxi Province of China (No. 2016GY-081), Fundamental Research Funds for the Central Universities (No.GK201402040), China Postdoctoral Science Foundation Special project (No.2014T70937) and Interdisciplinary Incubation Project of Learning Science of Shaanxi Normal University.

Author information

Authors and Affiliations

  1. Key Laboratory of Modern Teaching Technology, Ministry of Education, Xi’an, 710062, China

    Lingjun Li, Yali Peng & Shigang Liu

  2. School of Computer Science, Shaanxi Normal University, Xi’an, 710119, China

    Lingjun Li, Yali Peng, Guoyong Qiu, Zengguo Sun & Shigang Liu

Authors
  1. Lingjun Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yali Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Guoyong Qiu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zengguo Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shigang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yali Peng.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, L., Peng, Y., Qiu, G. et al. A survey of virtual sample generation technology for face recognition. Artif Intell Rev 50, 1–20 (2018). https://doi.org/10.1007/s10462-016-9537-z

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10462-016-9537-z

Keywords

Search

Navigation