DOI QR코드

DOI QR Code

Feature Extraction on a Periocular Region and Person Authentication Using a ResNet Model

ResNet 모델을 이용한 눈 주변 영역의 특징 추출 및 개인 인증

  • Kim, Min-Ki (Dept. of Computer Engineering, Gyeongsang National University Engineering Research Institute)
  • Received : 2019.10.11
  • Accepted : 2019.11.18
  • Published : 2019.12.31

Abstract

Deep learning approach based on convolution neural network (CNN) has extensively studied in the field of computer vision. However, periocular feature extraction using CNN was not well studied because it is practically impossible to collect large volume of biometric data. This study uses the ResNet model which was trained with the ImageNet dataset. To overcome the problem of insufficient training data, we focused on the training of multi-layer perception (MLP) having simple structure rather than training the CNN having complex structure. It first extracts features using the pretrained ResNet model and reduces the feature dimension by principle component analysis (PCA), then trains a MLP classifier. Experimental results with the public periocular dataset UBIPr show that the proposed method is effective in person authentication using periocular region. Especially it has the advantage which can be directly applied for other biometric traits.

Keywords

References

  1. F.P. Mahdi, M. Habib, A.R. Ahad, S. Mckeever, A.S.M. Moslehuddin, P. Vasant, “Face Recognition-based Real-time System for Surveillance,” Intelligent Decision Techniques, Vol. 11, No. 1, pp. 79-92, 2017. https://doi.org/10.3233/IDT-160279
  2. M. Uzair, A. Mahmood, A. Mian, and C. McDonald, "Periocular Region-based Person Identification in the Visible, Intrared and Hyperspectrul Imagery," Nurocomputing, Vol. 149, pp. 854-867, 2015. https://doi.org/10.1016/j.neucom.2014.07.049
  3. U. Park, R.R. Jillela, A. Ross, and A.K. Jain, “Periocular Biometrics in the Visible Spectrum,” IEEE Transaction on Information Forensics and Security, Vol. 6, No. 1, pp. 96-106, 2011. https://doi.org/10.1109/TIFS.2010.2096810
  4. C.N. Padole and H. Proenca, "Periocular Recognition: Analysis of Performance Degradation Factors," Proceedings of International Conference on Biometrics, pp. 439-445, 2012.
  5. J.M. Smereka and B.V. Kumar, "What is a 'Good' Periocular Region for Recognition?" Proceedings of the IEEE International Workshop on Computer Vision and Pattern Recognition, pp. 117-124, 2013.
  6. K.K. Kumar and M. Pavani, "LBP Based Biometric Identification Using the Periocular Region," Proceedings of IEEE Annual Information Technology, Electronics and Mobile Communication Conference, pp. 204-209, 2017.
  7. V.N. Boddeti, J.M. Smereka, and B.V. Kumar, "A Comparative Evaluation of Iris and Ocular Recognition Methods on Challenging Ocular Images," Proceedings of International Conference on Biometrics, pp. 1-8, 2011.
  8. A. Ross, R. Jillella, J.M. Smereka, V.N. Boddeti, B.V. Kumar, R. Barnard, et al., "Matching Highly Non-ideal Ocular Images: An Information Fusion Approach," Proceedings of International Conference on Biometrics, pp. 446-453, 2012.
  9. L. Nie, A. Kumar, and S. Zhan, "Periocular Recognition Using Unsupervised Convolutional RBM Feature Learning," Proceedings of International Conference on Pattern Recognition, pp. 399-404, 2014.
  10. A.F. Fernando, M. Anna, and B. Josef, "Compact Multi-scale Periocular Recognition Using SAFE Feature," Proceedings of International Conference on Pattern Recognition, pp. 1455-1460, 2016.
  11. D. Jia, D. Wei, S. Richard, L.J. Li, K. Li, F.F. Li., "ImageNet: A Large-scale Hierarchical Image Database," Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 248-255, 2009.
  12. A. Krizhevsky, I. Sutskever, and G.E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Proceedings of International Conference on Neural Information Processing System, Vol. 25, No. 2, pp. 1097-1105, 2012.
  13. M. Coskun, A. Ucar, O. Yidirim, Y. Demir, "Face Recognition Based on Convolutional Neural Network," Proceedings of International Conference on Modern Electrical and Energy Systems, pp. 376-379, 2017.
  14. M. Kim, “Contactless Palmprint Identification Using the Pretrained VGGNet Model,” Journal of Korea Multimedia Society, Vol. 21, No. 12, pp. 1439-1447, 2018. https://doi.org/10.9717/KMMS.2018.21.12.1439
  15. K. Nguyen, C. Fookes, A. Ross, and S. Sridharan, "Iris Recognition With Off-the-Shelf CNN Features: A Deep Learning Perspective," IEEE Access, Vol. 6, pp. 18848-18855, 2017. https://doi.org/10.1109/access.2017.2784352
  16. H.D. Kevin, A.F. Fernando, and B. Josef, "Periocular Recognition Using CNN Feature Off-the-Shelf," Proceedings of International Conference on Biometrics Special Interest Group, pp. 1-5, 2018.
  17. Z. Zhao and A. Jumar, “Improving Periocular Recognition by Explicit Attention to Critical Regions in Deep Neural Network,” IEEE Transaction on Information Forensics and Security, Vol. 13, No. 12, pp. 2937-2952, 2018. https://doi.org/10.1109/TIFS.2018.2833018
  18. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, et al., "Going Deeper with Convolutions," Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1-9, 2015.
  19. K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.