An adaptive approximation image reconstruction method for single sample problem in face recognition using FLDA

Abstract

Fisher linear discriminant analysis (FLDA) algorithm is a popular subspace method for face recognition, which requires that the number of training samples for each object is not less than two. In this paper, an adaptive approximation image reconstruction method based on economy singular value decomposition (ESVD) algorithm is proposed for the single sample problem in face recognition. By using ESVD the single training sample is decomposed to a set of basis images. Then an adaptive approximation image reconstruction method is proposed to reconstruct an approximation image by using several significant basis images. The single training image and its approximation image for each object form a new training set, which can make the FLDA be applied to the single sample problem in face recognition. The major contribution of the proposed work is that the number of significant basis images for the reconstruction of an approximation image is evaluated by using a reverse thinking approach based on experimental analysis. The performance of the proposed method is verified on the Yale, FERET, ORL, UMIST and AR face databases. The experimental results indicate that the proposed method is efficient and outperforms some existing methods which are proposed to overcome the single sample problem.