Joint Sparse Representation for Robust Multimodal Biometrics Recognition

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 rece...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on pattern analysis and machine intelligence Ročník 36; číslo 1; s. 113 - 126
Hlavní autoři:	Shekhar, Sumit, Patel, Vishal M., Nasrabadi, Nasser M., Chellappa, Rama
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Los Alamitos, CA IEEE 01.01.2014 IEEE Computer Society The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms Applied sciences Biometric Identification - methods Biometrics Biometrics (access control) Classification algorithms Computer science; control theory; systems Computer systems and distributed systems. User interface Databases, Factual Dermatoglyphics - classification Detection, estimation, filtering, equalization, prediction Exact sciences and technology Face - anatomy & histology feature fusion Humans Information, signal and communications theory Iris - anatomy & histology Joints Kernel Memory and file management (including protection and security) Memory organisation. Data processing Multimodal biometrics Optimization Robustness Signal and communications theory Signal, noise Software Sparse matrices sparse representation Telecommunications and information theory Biometrics Modeling Dimension reduction feature fusion Information source User interface Multiplicity Quality control Selection criterion Data fusion Sparse representation Multimodal interface Computer security Multimodal biometrics Mathematical programming
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	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 multimodal sparse representation method, 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 among biometric modalities. A multimodal quality measure is also proposed to weigh each modality as it gets fused. Furthermore, we also kernelize the algorithm to handle nonlinearity in data. The optimization problem is solved using an efficient alternative direction method. Various experiments show that the proposed method compares favorably with competing fusion-based methods.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 ObjectType-Article-2 ObjectType-Feature-1
ISSN:	0162-8828 1939-3539 2160-9292 1939-3539
DOI:	10.1109/TPAMI.2013.109