Quality-based score level fusion in multibiometric systems

Karthik Nandakumar; Yi Chen; Anil K. Jain; Sarat C. Dass

doi:10.1109/ICPR.2006.951

Quality-based score level fusion in multibiometric systems

Karthik Nandakumar, Yi Chen, Anil K. Jain, Sarat C. Dass

School of Mathematical & Computer Sciences

Research output: Chapter in Book/Report/Conference proceeding › Chapter

111 Citations (Scopus)

Abstract

The quality of biometric samples has a significant impact on the accuracy of a matcher. Poor quality biometric samples often lead to incorrect matching results because the features extracted from these samples are not reliable. Therefore, dynamically assigning weights to the outputs of individual matchers based on the quality of the samples presented at the input of the matchers can improve the overall recognition performance of a multibiometric system. We propose a likelihood ratio-based fusion scheme that takes into account the quality of the biometric samples while combining the match scores provided by the matchers. Instead of estimating the quality of the template and query images individually, we estimate a single quality metric for each template-query pair based on the local image quality measures. Experiments on a database of 320 users with iris and fingerprint modalities demonstrate the advantages of utilizing the quality information in multibiometric systems

Original language	English
Title of host publication	18th International Conference on Pattern Recognition (ICPR'06)
Publisher	IEEE
ISBN (Print)	0769525210
DOIs	https://doi.org/10.1109/ICPR.2006.951
Publication status	Published - 2006

Access to Document

10.1109/ICPR.2006.951

Cite this

@inbook{7f6eec9b31944354910694d622a53cc6,

title = "Quality-based score level fusion in multibiometric systems",

abstract = "The quality of biometric samples has a significant impact on the accuracy of a matcher. Poor quality biometric samples often lead to incorrect matching results because the features extracted from these samples are not reliable. Therefore, dynamically assigning weights to the outputs of individual matchers based on the quality of the samples presented at the input of the matchers can improve the overall recognition performance of a multibiometric system. We propose a likelihood ratio-based fusion scheme that takes into account the quality of the biometric samples while combining the match scores provided by the matchers. Instead of estimating the quality of the template and query images individually, we estimate a single quality metric for each template-query pair based on the local image quality measures. Experiments on a database of 320 users with iris and fingerprint modalities demonstrate the advantages of utilizing the quality information in multibiometric systems",

author = "Karthik Nandakumar and Yi Chen and Jain, {Anil K.} and Dass, {Sarat C.}",

year = "2006",

doi = "10.1109/ICPR.2006.951",

language = "English",

isbn = "0769525210",

booktitle = "18th International Conference on Pattern Recognition (ICPR'06)",

publisher = "IEEE",

address = "United States",

}

TY - CHAP

T1 - Quality-based score level fusion in multibiometric systems

AU - Nandakumar, Karthik

AU - Chen, Yi

AU - Jain, Anil K.

AU - Dass, Sarat C.

PY - 2006

Y1 - 2006

N2 - The quality of biometric samples has a significant impact on the accuracy of a matcher. Poor quality biometric samples often lead to incorrect matching results because the features extracted from these samples are not reliable. Therefore, dynamically assigning weights to the outputs of individual matchers based on the quality of the samples presented at the input of the matchers can improve the overall recognition performance of a multibiometric system. We propose a likelihood ratio-based fusion scheme that takes into account the quality of the biometric samples while combining the match scores provided by the matchers. Instead of estimating the quality of the template and query images individually, we estimate a single quality metric for each template-query pair based on the local image quality measures. Experiments on a database of 320 users with iris and fingerprint modalities demonstrate the advantages of utilizing the quality information in multibiometric systems

AB - The quality of biometric samples has a significant impact on the accuracy of a matcher. Poor quality biometric samples often lead to incorrect matching results because the features extracted from these samples are not reliable. Therefore, dynamically assigning weights to the outputs of individual matchers based on the quality of the samples presented at the input of the matchers can improve the overall recognition performance of a multibiometric system. We propose a likelihood ratio-based fusion scheme that takes into account the quality of the biometric samples while combining the match scores provided by the matchers. Instead of estimating the quality of the template and query images individually, we estimate a single quality metric for each template-query pair based on the local image quality measures. Experiments on a database of 320 users with iris and fingerprint modalities demonstrate the advantages of utilizing the quality information in multibiometric systems

U2 - 10.1109/ICPR.2006.951

DO - 10.1109/ICPR.2006.951

M3 - Chapter

SN - 0769525210

BT - 18th International Conference on Pattern Recognition (ICPR'06)

PB - IEEE

ER -

Quality-based score level fusion in multibiometric systems

Abstract

Access to Document

Fingerprint

Cite this