An geometrically intuitive marginal discriminant analysis method with application to face recognition

This paper presents a new nonparametric linear feature extraction method coined geometrically intuitive marginal discriminant analysis (IMDA). Motivated by the law of cosines in trigonometry, we characterize the square local margin by a weighted difference of the square between-class distance and the square within-class distance. Based on this characterization, we design a class margin criterion which is used to determine an optimal transform matrix such that the class margin is maximized in the transformed space. The proposed method was applied to face recognition and evaluated on the Yale and the FERET databases. Experimental results demonstrate the effectiveness of the proposed method.