UNIGE document Chapitre d'actes
previous document  unige:47806  next document
add to browser collection
Title

Error exponent analysis of person identification based on fusion of dependent/independent modalities

Authors
Published in Edward J. Delp III and Ping Wah Wong. Security, Steganography, and Watermarking of Multimedia Contents IX. San Jose (USA) - Jan 28-feb 1 - SPIE. 2007
Collection SPIE Proceedings; 6505
Abstract Abstract-Performance limits of multimodal detection systems are analyzed in this paper. Two main setups are analyzed, i.e., based on fusion of dependent and independent modalities, respectively. The analysis is performed in terms of attainable probability of detection errors characterized by the corresponding error exponents. It is demonstrated that an expected performance gain from fusion of dependent modalities is superior than in the case when one fuses independent signals. In order to quantify the efficiency of dependent modality fusion versus the independent case, the problem analysis is performed in the Gaussian formulation.
Keywords Data storageData transmissionDatabasesFingerprint recognition
Identifiers
Full text
Structures
Research groups Computer Vision and Multimedia Laboratory
Stochastic Information Processing Group
Multimodal Interaction Group
Citation
(ISO format)
KOVAL, Oleksiy, VOLOSHYNOVSKYY, Svyatoslav, PUN, Thierry. Error exponent analysis of person identification based on fusion of dependent/independent modalities. In: Edward J. Delp III and Ping Wah Wong (Ed.). Security, Steganography, and Watermarking of Multimedia Contents IX. San Jose (USA). [s.l.] : SPIE, 2007. (SPIE Proceedings; 6505) https://archive-ouverte.unige.ch/unige:47806

93 hits

33 downloads

Update

Deposited on : 2015-03-06

Export document
Format :
Citation style :