Video-based Face Recognition via Joint Sparse Representation

Published

January 2, 2013

Author(s)

P J. Phillips, Vishal M. Patel, Yi-Chen Chen, Rama Chellappa

Abstract

In video-based face recognition, a key challenge is in exploiting the extra information available in a video. In addition, different video sequences of the same subject may contain variations in resolution, illumination, pose, and facial expressions. These variations contribute to the challenges in designing an effective video-based face-recognition algorithm. We propose a novel multivariate sparse representation method for video-to-video face recognition. Our method simultaneously takes into account correlations as well as coupling information among the video frames. Our method jointly represents all the video data by a sparse linear combination of training data. In addition, we modify our model so that it is robust to noise and occlusion. Furthermore, we kernelize the algorithm to handle the non-linearities present in video data. Numerous experiments using unconstrained video sequences show that our method is effective and performs significantly better than many competitive video-based face recognition algorithms.

Citation

NIST Interagency/Internal Report (NISTIR) - 7906

Report Number

7906

NIST Pub Series

NIST Interagency/Internal Report (NISTIR)

Pub Type

NIST Pubs

Download Paper

https://doi.org/10.6028/NIST.IR.7906

Citation

Phillips, P. , Patel, V. , Chen, Y. and Chellappa, R. (2013), Video-based Face Recognition via Joint Sparse Representation, NIST Interagency/Internal Report (NISTIR), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.IR.7906 (Accessed October 10, 2025)