Currently, I'm an undergraduated student, supervised by Yun-Hao Yuan, at Yangzhou University. My research interests focus on image super-resolution and multi-view learning. I will further my research on computer version under Prof. Mingming Cheng's supervision at Nankai University. For more information, please consult my 8145249284.
Authors: Yun-Hao Yuan, Zhao Zhang, Yun Li, Ji-Peng Qiang, Bin Li, Xiao-Bao Shen
We propose a scale-adaptive LR face recognition approach based on two-dimensional multi-set canonical correlation analysis (2DMCCA), where face image matrix does not need to be previously transformed into a vector. In the proposed method, training sets with different resolutions are treated as different views, and then projected in parallel into a latent coherent space where the consistency of multi-view face data is maximally enhanced. When a new LR face image with an arbitrary scale is input, we first transform it by using the left and right projection matrices of an appropriate training view, and then reconstruct its HR facial feature by neighborhood reconstruction.
Authors: Zhao Zhang, Yun-Hao Yuan, Xiao-bo Shen, Yun Li
We propose a new LR face recognition and reconstruction method using deep canonical correlation analysis (DCCA). Unlike linear CCA-based methods, our proposed method can learn flexible nonlinear representations by passing LR and high-resolution (HR) image principal component features through multiple stacked layers of nonlinear transformation. As the nonlinear transformation in deep neural networks is implicit, we apply radial basis function based neural network to learn an explicit mapping between principal components and correlational features. In addition, we also design two residual compensation methods for identification and vision enhancement, respectively.
Authors: Zhao Zhang, Yun-Hao Yuan, Yun Li, Bin Li, Ji-Peng Qiang
Canonical correlation analysis (CCA) is a classical but powerful tool for image super-resolution tasks. Since CCA in essence is a linear projection learning method, it usually fails to uncover the nonlinear relationships between high-resolution (HR) and low-resolution (LR) facial image features. In order to solve this issue, we propose a new face hallucination and recognition algorithm based on kernel CCA, where the nonlinear correlation between HR and LR face features can be well depicted by implicit HR nonlinear mappings determined by specific kernels. First, our proposed method respectively extracts the principal component features from HR and LR facial images for computational efficiency and noise removal. Then, it makes use of kernel CCA to learn the nonlinear consistency of HR and LR facial features.