Kernel nonnegative matrix factorization with RBF kernel function for face recognition
Wen-Sheng Chen, Xian-Kun Huang, Binbin Fan, Qian Wang, Baohua Wang · 2017
This paper attempts to represent the mapped data in the radial basis function (RBF) feature space under non-negativity constraints and develops a RBF kernel based non-negative matrix factorization (KNMF-RBF) algorithm. Based on an objective function with Frobenius norm, we obtain the multiplicative update rules of our KNMF-RBF approach using kernel theory and gradient descent method. The proposed KNMF-RBF method is theoretically shown to be convergence by means of the constructed auxiliary function. Our approach is successfully applied to face recognition in the FERET face database. Experimental results demonstrate that the proposed KNMF-RBF method surpasses some kernel based methods. The results are encouraging.