Fractional discriminative multiview correlation projection for face feature fusion

Multiple view data with different feature representations have widely arisen in various practical applications. Due to the information diversity, fusing multiview features is very valuable for classification purpose. In this paper, we propose a new multifeature fusion method called fractional-order discriminative multiview correlation projection (FDMCP), which is based on fractional-order scatter matrices with class label information of the samples. FDMCP first defines supervised covariance matrices in each view. It then constructs fractional supervised scatter matrices. Experimental results on three benchmark face image datasets show that our proposed FDMCP approach outperforms generalized multiview linear discriminant analysis.