Skip to main content
SpringerLink
Log in

A New Score Level Fusion Approach for Stable User Verification System Using the PPG Signal

  • Published:
Journal of Signal Processing Systems Aims and scope Submit manuscript

Abstract

The recent advances in AI have made significant progress in several applications including biometric recognition. In this work, we utilize a specific biometric modality, photoplethysmography signal, for user verification systems. This physiological signal consists of user-specific features that make it suitable to authenticate a user. Yet, to be applied in realistic scenarios, time-stable features should be developed as well. Therefore, we propose a variation-stable approach tested on four score fusion techniques to find unique and time-stable features. We evaluate the proposed system on databases collected from single- and two-sessions. In the earlier, the training and testing are done solely on one session data to find user-specific features, while the second scenario is performed on data from two different sessions to investigate the time permanence of the features. The outcomes demonstrate the superiority of the proposed verification system simulated on three public datasets and one database collected for this work.

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

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8

Similar content being viewed by others

References

  1. Galbally, J., Fierrez, J., Alonso-Fernandez, F., et al. (2011). Evaluation of direct attacks to fingerprint verification systems. Telecommunication Systems, 47(3), 243–254.

    Article  Google Scholar 

  2. Hadid, A. (2014). Face biometrics under spoofing attacks: Vulnerabilities, countermeasures, open issues, and research directions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 113–118).

  3. Hwang, D. Y., Taha, B., & Hatzinakos, D. (2021b). Variation-stable fusion for PPG-based biometric system. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 8042–8046). IEEE.

  4. Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015). Deep face recognition. British Machine Vision Association.

  5. Kumar, A., & Kwong, C. (2013). Towards contactless, low-cost and accurate 3D fingerprint identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3438–3443).

  6. Zhao, Z., & Kumar, A. (2017). Towards more accurate iris recognition using deeply learned spatially corresponding features. In Proceedings of the IEEE international conference on computer vision (pp. 3809–3818).

  7. Agrafioti, F., & Hatzinakos, D. (2010). Signal validation for cardiac biometrics. In 2010 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 1734–1737).

  8. Hari, S., Agrafioti, F., & Hatzinakos, D. (2013). Design of a hamming-distance classifier for ECG biometrics. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 3009–3012).

  9. Lourenço, A., Silva, H., & Fred, A. (2011). Unveiling the biometric potential of finger-based ECG signals. Computational Intelligence and Neuroscience, 1–8.

  10. Gu, Y. Y., Zhang, Y., & Zhang, Y. T. (2003). A novel biometric approach in human verification by photoplethysmographic signals. In 4th International IEEE EMBS Special Topic Conference on Information Technology Applications in Biomedicine (pp. 13–14).

  11. Elgendi, M. (2012). On the analysis of fingertip photoplethysmogram signals. Current Cardiology Reviews, 8(1), 14–25.

    Article  Google Scholar 

  12. Gu, Y. Y., & Zhang, Y. T. (2003). Photoplethysmographic authentication through fuzzy logic. In IEEE EMBS Asian-Pacific Conference on Biomedical Engineering (pp. 136–137).

  13. Sancho, J., Alesanco, Á., & García, J. (2018). Biometric authentication using the PPG: A long-term feasibility study. Sensors, 18(5), 1525.

    Article  Google Scholar 

  14. Karimian, N., Guo, Z., Tehranipoor, M., et al. (2017a) Human recognition from photoplethysmography (PPG) based on non-fiducial features. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 4636–4640).

  15. Karimian, N., Tehranipoor, M., & Forte, D. (2017b). Non-fiducial PPG-based authentication for healthcare application. In 2017 IEEE EMBS International Conference on Biomedical Health Informatics (BHI) (pp. 429–432).

  16. Biswas, D., Everson, L., Liu, M., et al. (2019). Cornet: Deep learning framework for PPG-based heart rate estimation and biometric identification in ambulant environment. IEEE Transactions on Biomedical Circuits and Systems, 13(2), 282–291.

    Article  Google Scholar 

  17. Everson, L., Biswas, D., Panwar, M., et al. (2018). Biometricnet: Deep learning based biometric identification using wrist-worn PPG. In 2018 IEEE International Symposium on Circuits and Systems (ISCAS) (pp. 1–5)

  18. Hwang, D., & Hatzinakos, D. (2019). PPG-based personalized verification system - PPSNET. In Presented at 2019 IEEE Canadian Conference of Electrical and Computer Engineering (CCECE).

  19. Akhtar, Z., Fumera, G., Marcialis, G. L., et al. (2012). Evaluation of multimodal biometric score fusion rules under spoof attacks. In 2012 5th IAPR International Conference on Biometrics (ICB) (pp. 402–407). IEEE.

  20. Luque, J., Cortes, G., Segura, C., et al. (2018). End-to-end photopleth ysmography (PPG) based biometric authentication by using convolutional neural networks. 2018 26th European Signal Processing Conference (EUSIPCO) (pp. 538–542)

  21. Hammad, M., & Wang, K. (2019). Parallel score fusion of ECG and fingerprint for human authentication based on convolution neural network. Computers & Security, 81, 107–122.

    Article  Google Scholar 

  22. Su, K., Yang, G., Wu, B., et al. (2019). Human identification using finger vein and ECG signals. Neurocomputing, 332, 111–118.

    Article  Google Scholar 

  23. Dwivedi, R., & Dey, S. (2019). Score-level fusion for cancelable multi-biometric verification. Pattern Recognition Letters, 126, 58–67.

    Article  Google Scholar 

  24. Hwang, D. Y., Taha, B., & Hatzinakos, D. (2021a). PBGAN: Learning PPG representations from GAN for time-stable and unique verification system. IEEE Transactions on Information Forensics and Security, 16, 5124–5137.

  25. Arteaga-Falconi, J., Osman, H. A., & Saddik, A. E. (2015). R-peak detection algorithm based on differentiation. In 2015 IEEE 9th International Symposium on Intelligent Signal Processing (WISP) Proceedings (pp. 1–4).

  26. Ram, M. R., Madhav, K. V., Krishna, E. H., et al. (2012). A novel approach for motion artifact reduction in PPG signals based on AS-LMS adaptive filter. IEEE Transactions on Instrumentation and Measurement, 61(5), 1445–1457.

    Article  Google Scholar 

  27. Verma, A., Cabrera, S., Mayorga, A., et al. (2013). A robust algorithm for derivation of heart rate variability spectra from ECG and PPG signals. In 2013 29th Southern Biomedical Engineering Conference (pp. 35–36). IEEE.

  28. Huang, B., & Kinsner, W. (2002). ECG frame classification using dynamic time warping. In IEEE CCECE2002. Canadian Conference on Electrical and Computer Engineering. Conference Proceedings (Cat. No.02CH37373) (pp. 1105–1110).

  29. Li, Q., & Clifford, G. D. (2012). Dynamic time warping and machine learning for signal quality assessment of pulsatile signals. Physiological Measurement, 33(9), 1491–1501.

    Article  Google Scholar 

  30. Mohamed, M., & Deriche, M. (2014). An approach for ECG feature extraction using daubechies 4 (db4) wavelet. International Journal of Computer Applications, 96(12), 36–41.

    Article  Google Scholar 

  31. Hwang, D. Y., Taha, B., Lee, D. S., et al. (2021). Evaluation of the time stability and uniqueness in PPG-based biometric system. IEEE Transactions on Information Forensics and Security, 16, 116–130.

    Article  Google Scholar 

  32. Damer, N., Opel, A., Shahverdyan, A., et al. (2013). An overview on multi-biometric score-level fusion-verification and identification. In ICPRAM (pp. 647–653).

  33. Karlen, W., Raman, S., Ansermino, J. M., et al. (2013). Multiparameter respiratory rate estimation from the photoplethysmogram. IEEE Transactions on Biomedical Engineering, 60(7), 1946–1953.

    Article  Google Scholar 

  34. Zhang, Z., Pi, Z., & Liu, B. (2015). Troika: A general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise. IEEE Transactions on Biomedical Engineering, 62(2), 522–531.

    Article  Google Scholar 

  35. Yadav, U., Abbas, S. N., & Hatzinakos, D. (2018). Evaluation of PPG biometrics for authentication in different states. In 2018 International Conference on Biometrics (ICB) (pp. 277–282).

  36. Piciucco, E., Di Lascio, E., Maiorana, E., et al. (2021). Biometric recognition using wearable devices in real-life settings. Pattern Recognition Letters, 146, 260–266.

    Article  Google Scholar 

Download references

Acknowledgements

This work was partially supported by the Natural Sciences and Engineering Research Council of Canada (NSERC) and the Royal Bank of Canada (RBC).

Author information

Authors and Affiliations

  1. Electrical and Computer Engineering Dept., University of Toronto, Toronto, ON, Canada

    Dae Yon Hwang, Bilal Taha & Dimitrios Hatzinakos

  2. Vector Institute for Artificial Intelligence, Toronto, ON, Canada

    Bilal Taha

Authors
  1. Dae Yon Hwang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bilal Taha
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dimitrios Hatzinakos
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dae Yon Hwang.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hwang, D.Y., Taha, B. & Hatzinakos, D. A New Score Level Fusion Approach for Stable User Verification System Using the PPG Signal. J Sign Process Syst 94, 787–798 (2022). https://doi.org/10.1007/s11265-022-01747-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11265-022-01747-6

Keywords

Search

Navigation