Skip to main content
SpringerLink
Log in

Multi-source deep transfer learning for cross-sensor biometrics

  • IBPRIA 2015
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Deep transfer learning emerged as a new paradigm in machine learning in which a deep model is trained on a source task and the knowledge acquired is then totally or partially transferred to help in solving a target task. In this paper, we apply the source–target–source methodology, both in its original form and an extended multi-source version, to the problem of cross-sensor biometric recognition. We tested the proposed methodology on the publicly available CSIP image database, achieving state-of-the-art results in a wide variety of cross-sensor scenarios.

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
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Dai W, Xue GR, Yang Q, Yu Y (2007) Co-clustering based classification for out-of-domain documents. In: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, pp 210–219

  2. Yang J, Yan R, Hauptmann AG (2007) Cross-domain video concept detection using adaptive svms. In: Proceedings of the 15th international conference on Multimedia. ACM, pp 188–197

  3. Blitzer J, Dredze M, Pereira F et al (2007) Biographies, bollywood, boom-boxes and blenders: domain adaptation for sentiment classification. ACL 7:440–447

    Google Scholar 

  4. Dahlmeier D, Ng HT (2010) Domain adaptation for semantic role labeling in the biomedical domain. Bioinformatics 26(8):1098–1104

    Article  Google Scholar 

  5. Pan SJ, Shen D, Yang Q, Kwok JT (2008) Transferring localization models across space. In: AAAI, pp 1383–1388

  6. Kandaswamy C, Silva LM, Cardoso JS (2015) Source-target-source classification using stacked denoising autoencoders. In: Pattern recognition and image analysis. Springer, pp 39–47

  7. Caruana R (1997) Multitask learning. Mach Learn 28(1):41–75

    Article  MathSciNet  Google Scholar 

  8. Thrun S (1998) Lifelong learning algorithms. In: Learning to learn. Springer, pp 181–209

  9. Daume III H, Marcu D (2006) Domain adaptation for statistical classifiers. J Artif Intell Res 26:101–126

    MathSciNet  MATH  Google Scholar 

  10. Glorot X, Bordes A, Bengio Y (2011) Domain adaptation for large-scale sentiment classification: a deep learning approach. In Proceedings of the 28th international conference on machine learning (ICML-11), pp 513–520

  11. Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Vaughan JW (2010) A theory of learning from different domains. Mach Learn 79(1–2):151–175

    Article  MathSciNet  Google Scholar 

  12. Bruzzone L, Marconcini M (2010) Domain adaptation problems: a DASVM classification technique and a circular validation strategy. IEEE Trans Pattern Anal Mach Intell 32(5):770–787

    Article  Google Scholar 

  13. Ciresan D, Meier U, Schmidhuber J (2012) Multi-column deep neural networks for image classification. In: 2012 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 3642–3649

  14. Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? In: Advances in neural information processing systems, pp 3320–3328

  15. Kandaswamy C, Silva LM, Alexandre LA, Santos JM, de Sá JM (2014) Improving deep neural network performance by reusing features trained with transductive transference. In: Artificial neural networks and machine learning—ICANN 2014. Springer, pp 265–272

  16. Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 35(8):1798–1828

    Article  Google Scholar 

  17. Connaughton R, Sgroi A, Bowyer KW, Flynn P (2011) A cross-sensor evaluation of three commercial iris cameras for iris biometrics. In: IEEE computer society conference on computer vision and pattern recognition workshops (CVPRW). IEEE, pp 90–97

  18. Monteiro JC, Esteves R, Santos G, Fiadeiro PT, Lobo J, Cardoso JS (2015) A comparative analysis of two approaches to periocular recognition in mobile scenarios. In: Advances in visual computing, vol. 9475 of Lecture Notes in Computer Science. Springer International Publishing, pp 268–280

  19. Pillai J, Puertas M, Chellappa R (2014) Cross-sensor iris recognition through Kernel learning. IEEE Trans Pattern Anal Mach Intell 36:73–85

    Article  Google Scholar 

  20. Santos G, Grancho E, Bernardo MV, Fiadeiro PT (2015) Fusing iris and periocular information for cross-sensor recognition. Pattern Recogn Lett 57:52–59

    Article  Google Scholar 

  21. Jillela R, Ross A (2014) Matching face against iris images using periocular information. In: 2014 IEEE international conference on image processing (ICIP). IEEE, pp 4997–5001

  22. Woodard DL, Pundlik S, Miller P, Jillela R, Ross A (2010) On the fusion of periocular and iris biometrics in non-ideal imagery. In: 2010 20th international conference on pattern recognition (ICPR). IEEE, pp 201–204

  23. Shao L, Zhu F, Li X (2015) Transfer learning for visual categorization: a survey. IEEE Trans Neutral Netw Learn Syst 26(5):1019–1034

    Article  MathSciNet  Google Scholar 

  24. Monteiro JC, Cardoso JS (2015) Periocular recognition under unconstrained settings with universal background models. In: Proceedings of the international conference on bio-inspired systems and signal processing (BIOSIGNALS)

  25. Reynolds DA, Quatieri TF, Dunn RB (2000) Speaker verification using adapted Gaussian mixture models. Digit Signal Process 10(1):19–41

    Article  Google Scholar 

  26. JCM et al (2015) Periocular recognition in mobile scenarios: a comparative analysis of two approaches. In: Proceedings of 11th international symposium on visual computing (ISVC)

  27. Campbell WM, Sturim DE, Reynolds DA (2006) Support vector machines using gmm supervectors for speaker verification. IEEE Signal Process Lett 13(5):308–311

    Article  Google Scholar 

  28. Ge Z, McCool C, Sanderson C, Corke P (2015) Modelling local deep convolutional neural network features to improve fine-grained image classification. arXiv preprint arXiv:1502.07802

  29. Kandaswamy C, Silva LM, Alexandre L, Sousa R, Santos JM, de Sá JM et al (2014) Improving transfer learning accuracy by reusing stacked denoising autoencoders. In: 2014 IEEE international conference on systems, man and cybernetics (SMC). IEEE, pp 1380–1387

  30. Tan T, He Z, Sun Z (2010) Efficient and robust segmentation of noisy iris images for non-cooperative iris recognition. Image Vis Comput 28(2):223–230

    Article  Google Scholar 

  31. Proença H, Alexandre L (2007) The NICE. I: noisy iris challenge evaluation—part I. In: First IEEE international conference on biometrics: theory, applications, and systems. IEEE, pp 1–4

Download references

Acknowledgments

This work was financed by FEDER funds through the Programa Operacional Factores de Competitividade—COMPETE and by Portuguese funds through FCT—Fundação para a Ciência e Tecnologia in the framework of the project PTDC/EIA-EIA/119004/2010. The second author would like to thank Fundação para a Ciência e Tecnologia (FCT)—Portugal the financial support for the PhD grant SFRH/BD/87392/2012.

Author information

Authors and Affiliations

  1. i3S and INEB, Universidade do Porto, Porto, Portugal

    Chetak Kandaswamy & Luís M. Silva

  2. INESC TEC and Faculdade de Engenharia, Universidade do Porto, Porto, Portugal

    Chetak Kandaswamy, João C. Monteiro & Jaime S. Cardoso

  3. Departamento de Matemática, Universidade de Aveiro, Aveiro, Portugal

    Chetak Kandaswamy & Luís M. Silva

Authors
  1. Chetak Kandaswamy
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. João C. Monteiro
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Luís M. Silva
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jaime S. Cardoso
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chetak Kandaswamy.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kandaswamy, C., Monteiro, J.C., Silva, L.M. et al. Multi-source deep transfer learning for cross-sensor biometrics. Neural Comput & Applic 28, 2461–2475 (2017). https://doi.org/10.1007/s00521-016-2325-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-016-2325-5

Keywords

Search

Navigation