logo

SCIENCE CHINA Information Sciences, Volume 63 , Issue 1 : 119103(2020) https://doi.org/10.1007/s11432-018-9862-9

The FrFT convolutional face: toward robust face recognition using the fractional Fourier transform and convolutional neural networks

More info
  • ReceivedAug 26, 2018
  • AcceptedMar 15, 2019
  • PublishedOct 16, 2019

Abstract

There is no abstract available for this article.


Acknowledgment

This work was supported in part by National Natural Science Foundation of China (Grant Nos. 61421001, U1833203).


References

[1] Hong D F, Liu W Q, Su J. A novel hierarchical approach for multispectral palmprint recognition. Neurocomputing, 2015, 151: 511-521 CrossRef Google Scholar

[2] Li X L, Cui G S, Dong Y S. Discriminative and Orthogonal Subspace Constraints-Based Nonnegative Matrix Factorization. ACM Trans Intell Syst Technol, 2018, 9: 1-24 CrossRef Google Scholar

[3] Hong D F, Liu W Q, Wu X. Robust palmprint recognition based on the fast variation Vese-Osher model. Neurocomputing, 2016, 174: 999-1012 CrossRef Google Scholar

[4] Li X L, Cui G S, Dong Y S. Graph Regularized Non-Negative Low-Rank Matrix Factorization for Image Clustering.. IEEE Trans Cybern, 2017, 47: 3840-3853 CrossRef PubMed Google Scholar

[5] Li X L, Lu Q M, Dong Y S. SCE: A Manifold Regularized Set-Covering Method for Data Partitioning.. IEEE Trans Neural Netw Learning Syst, 2018, 29: 1760-1773 CrossRef PubMed Google Scholar

[6] Li X L, Cui G S, Dong Y S. Refined-Graph Regularization-Based Nonnegative Matrix Factorization. ACM Trans Intell Syst Technol, 2017, 9: 1-21 CrossRef Google Scholar

[7] Wang X, Qi L, Tie Y, et al. Face recognition based on the band fusion of generalized phase spectrum of 2D-FrFT. In: Proceedings of the International Conference on Graphics and Image Processing (ICGIP), 2016. 685: 137--145. Google Scholar

[8] Lecun Y, Bottou L, Bengio Y. Gradient-based learning applied to document recognition. Proc IEEE, 1998, 86: 2278-2324 CrossRef Google Scholar

[9] Hong D F, Yokoya N, Xu J, et al. Joint & progressive learning from high-dimensional data for multi-label classification. In: Proceedings of the European Conference on Computer Vision (ECCV), 2018. 469--484. Google Scholar

  • Figure 1

    (Color online) (a) The proposed network architecture and (b) quantitative comparisons using different $p$ values and network ablation study on two face datasets.

Copyright 2020  CHINA SCIENCE PUBLISHING & MEDIA LTD.  中国科技出版传媒股份有限公司  版权所有

京ICP备14028887号-23       京公网安备11010102003388号