Proceedings chapter
OA Policy
English

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

Presented atSan Jose (USA), Jan 28-feb 1
Published inEdward J. Delp III and Ping Wah Wong (Ed.), Security, Steganography, and Watermarking of Multimedia Contents IX
PublisherSPIE
Collection
  • SPIE Proceedings; 6505
Publication date2007
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 storage
  • Data transmission
  • Databases
  • Fingerprint recognition
Citation (ISO format)
KOVAL, Oleksiy, VOLOSHYNOVSKYY, Svyatoslav, PUN, Thierry. Error exponent analysis of person identification based on fusion of dependent/independent modalities. In: Security, Steganography, and Watermarking of Multimedia Contents IX. Edward J. Delp III and Ping Wah Wong (Ed.). San Jose (USA). [s.l.] : SPIE, 2007. (SPIE Proceedings) doi: 10.1117/12.704138
Main files (1)
Proceedings chapter (Published version)
accessLevelPublic
Identifiers
564views
387downloads

Technical informations

Creation06/03/2015 17:12:15
First validation06/03/2015 17:12:15
Update14/03/2023 22:59:16
Status update14/03/2023 22:59:16
Last indexation30/10/2024 23:20:47
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack