Abstract:
In many automatic face recognition applications, a set of a person's face images is available rather than a single image. In this paper, we describe a novel method for fa...Show MoreMetadata
Abstract:
In many automatic face recognition applications, a set of a person's face images is available rather than a single image. In this paper, we describe a novel method for face recognition using image sets. We propose a flexible, semi-parametric model for learning probability densities confined to highly non-linear but intrinsically low-dimensional manifolds. The model leads to a statistical formulation of the recognition problem in terms of minimizing the divergence between densities estimated on these manifolds. The proposed method is evaluated on a large data set, acquired in realistic imaging conditions with severe illumination variation. Our algorithm is shown to match the best and outperform other state-of-the-art algorithms in the literature, achieving 94% recognition rate on average.
Published in: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
Date of Conference: 20-25 June 2005
Date Added to IEEE Xplore: 25 July 2005
Print ISBN:0-7695-2372-2
Print ISSN: 1063-6919