Semi-supervised Marginal Fisher Analysis

Abstract

Marginal Fisher Analysis(MFA) is a typical supervised subspace embedding method which has been used in dimensionality reduction. The projection matrixes are obtained by maximizing the intraclass compactness and simultaneously minimizing the intraclass separability. But in practical applications, no sufficient labeled training samples with prior knowledge was provided, so unlabeled image data are eager for incorporating in subspace learning algorithm to improve the identification accuracy. In this paper, we propose a semi supervised learning algorithm, which is called semi-supervised Marginal Fisher Analysis(SMFA). Not only the labeled data points are used to maximize the separability between different classes, but also the unlabeled data points are used to estimate the intrinsic geometric structure of the data. Therefore, we design a discriminant function which is as smooth as possible on the data manifold. Experimental results demonstrate that our SMFA algorithm outperforms the start-of-art methods.