Projection twin SMMs for 2d image data classification
Haitao Gao · 2015
In this paper, we propose a matrix version extension for linear regularization projection twin support vector machine presented by Shao et al. (Knowl Based Syst 37:203-210, 2013), named as linear projection twin sup- port matrix machine (linear projection twin support matrix machine (PTSMM)), for 2d image data classification. In order to discuss the nonlinear version of PTSMM, a new matrix kernel function is introduced and based on which, we provide a nonlinear PTSMM algorithm with a detailed theoretical derivation. To examine the effectiveness of the presented linear and nonlinear PTSMM, we perform comparative experiments with three linear classifiers sup- port tensor machines, twin support tensor machine and proximal support tensor machine on ORL, YALE and AR databases. Experimental results show that our methods are effective and efficient.