Learning Fractional Orthogonal Latent Consistent Features for Face Hallucination and Recognition

Yun-Hao Yuan, Jin Li, Yun Li, Jipeng Qiang, Bin Li

Abstract

Face hallucination (FH) is a powerful technique to reconstruct high-resolution (HR) faces from low-resolution (LR) faces. Most of conventional FH techniques ignore the influence of small training data, which may lead to the bias of variance and covariance. In this paper, we propose a novel FH method via fractional orthogonal latent consistent features that we call fractional orthogonal partial least squares based FH (FOPLSFH). In the proposed FOPLS-FH, intra- and cross-resolution covariance matrices are re-estimated through fractional-order eigenvalues and singular values modeling. Experimental results on real-world face datasets demonstrate the effectiveness of the proposed FOPLS-FH method.
BibTeX
@inproceedings{yuan2020learning,
  author = {Yun-Hao Yuan and Jin Li and Yun Li and Jipeng Qiang and Bin Li},
  title = {{Learning Fractional Orthogonal Latent Consistent Features for Face Hallucination and Recognition}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2020},
  doi = {10.1109/icassp40776.2020.9054449},
}

Loading related content...

Figure