Joint sparsity-based robust multimodal biometrics recognition

Authors:
Sumit Shekhar;Vishal M. Patel;Nasser M. Nasrabadi;Rama Chellappa
Affiliations:
University of Maryland, College Park;University of Maryland, College Park;Army Research Lab, Adelphi;University of Maryland, College Park
Venue:
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Year:
2012

Citing 6
Cited 0

A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Sparse Multinomial Logistic Regression: Fast Algorithms and Generalization Bounds

IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Face Recognition via Sparse Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Alternating Direction Algorithms for $\ell_1$-Problems in Compressive Sensing

SIAM Journal on Scientific Computing
Filterbank-based fingerprint matching

IEEE Transactions on Image Processing
An Augmented Lagrangian Approach to the Constrained Optimization Formulation of Imaging Inverse Problems

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Traditional biometric recognition systems rely on a single biometric signature for authentication. While the advantage of using multiple sources of information for establishing the identity has been widely recognized, computational models for multimodal biometrics recognition have only recently received attention. We propose a novel multimodal multivariate sparse representation method for multimodal biometrics recognition, which represents the test data by a sparse linear combination of training data, while constraining the observations from different modalities of the test subject to share their sparse representations. Thus, we simultaneously take into account correlations as well as coupling information between biometric modalities. Furthermore, the model is modified to make it robust to noise and occlusion. The resulting optimization problem is solved using an efficient alternative direction method. Experiments on a challenging public dataset show that our method compares favorably with competing fusion-based methods.