Multibiometrics Enhancement Using Quality Measurement in Score Level Fusion

Artabaz, Saliha; Sliman, Layth; Dellys, Hachemi Nabil; Benatchba, Karima; Koudil, Mouloud

doi:10.1007/978-3-319-53480-0_26

Cited by 4 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Year Fusion Rule Biometric Traits [19] 2015 weighted-sum rule Voice and face [18] 2019 PSO-DS Palmprint, iris, face [20] 2015 weighted-sum rule Face and iris [21] 2016 weighted-sum rule Face and iris [22] 2017 weighted-sum rule Face and iris [23] 2017 Quality-based weights Voice and face [24] 2018 DSmT-based rule Face and Fingerprint [25] 2019 Backtracking Search, PCR Iris, finger-vein and fingerprint [26] 2020 weighted-sum rule Finger-vein…”

Section: Methodsmentioning

confidence: 99%

An Approach for Full Reinforcement-Based Biometric Score Fusion

Cheniti,

Akhtar,

Adak

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Multibiometric systems have the potential to mitigate error rates and address certain inherent weaknesses found in unimodal systems. This study introduces an innovative scheme for user recognition in multibiometric systems, centered on a score-level fusion framework. The foundation of this framework lies in the full reinforcement operator (FRO), specifically estimating FRO through generator functions associated with triangular norms (T-norms and T-conorm). The efficiency of the proposed method has been showcased through an extensive set of experiments carried out on four commonly available benchmark databases: all three partitions of the National Institute of Standards and Technology (NIST) databases (Set 1, 2, 3), along with the XM2VTS database. Our method achieves superior accuracy compared to existing methods, reaching 100 % recognition on NIST-Set 1, 93.40 % on NIST-Set 2, and 94.54 % on the more challenging NIST-Set 3. The experimental findings illustrate that score fusion schemes based on FRO not only enhance verification rates when compared to current score-level fusion techniques (such as Asymmetric Aggregation Operators, Minimum, Maximum, T-norms, and Symmetric-Sum) but also offer a swift computational performance. INDEX TERMS Unidiomatic system, multibiometric system, score-level fusion, full reinforcement operator (FRO).

show abstract

Section: Methodsmentioning

confidence: 99%

An Approach for Full Reinforcement-Based Biometric Score Fusion

Cheniti,

Akhtar,

Adak

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Eisenbach et al [13] proposed likelihood ratio-based score normalisation and the normalised scores are fused using weighted sum rule, where weights are estimated by pairwise optimisation of projected genuine-impostor overlap Pairwise optimization of projected genuine-impostor overlap (PROPER) method. Various other weighting techniques are also proposed in the recent literature: query-adaptive feature weighting [14], score reliability-based weighting [15] and quality-based weights [16]. Major challenges in transformation-based techniques are the selection of normalisation techniques and its weight parameters which are training dependent and require extensive experiments.…”

Section: Related Workmentioning

confidence: 99%

Score‐level fusion using generalized extreme value distribution and DSmT, for multi‐biometric systems

2018

View full text Add to dashboard Cite

Human recognition in a multi-biometric system is performed by combining biometric clues from different sources (multiple sensors, units, algorithms, samples and modalities) at different levels (sensor, feature, score, rank and decision level). Low computational complexity and adequate data for fusion make the score-level fusion a preferable option over other levels of fusion. However, incompatibility issue prevails at this level as scores obtained from different uni-biometric systems are disparate in nature. This disparity can be resolved by using score normalisation before fusion. This study first analysed the effect of generalised extreme value distribution-based score normalisation technique on different fusion techniques and then proposes an efficient score fusion technique based on Dezert-Smarandache theory (DSmT). A unique blend of belief assignment and decision-making methods in the DSmT framework is proposed for score-level fusion. For evaluation of the proposed method, experiments are performed on multi-algorithm, multi-unit and multi-modal biometrics systems created from three publicly available datasets: (i) NIST BSSR1 multi-biometric score database, (ii) face recognition grand challenge (FRGC) V2.0 and (iii) LG4000 iris dataset. Comparative studies of performance analysis show the efficiency of the authors' proposed method over other recently published state-of-the-art fusion methods.

show abstract

Weighted quasi‐arithmetic mean based score level fusion for multi‐biometric systems

Herbadji¹,

Guermat²,

Ziet

et al. 2020

IET biom.

View full text Add to dashboard Cite

Biometrics is now being principally employed in many daily applications ranging from the border crossing to mobile user authentication. In the high-security scenarios, biometrics require stringent accuracy and performance criteria. Towards this aim, multi-biometric systems that fuse the evidences from multiple sources of biometric have exhibited to diminish the error rates and alleviate inherent frailties of the individual biometric systems. In this article, a novel scheme for score-level fusion based on weighted quasi-arithmetic mean (WQAM) has been proposed. Specifically, WQAMs are estimated via different trigonometric functions. The proposed fusion scheme encompasses properties of both weighted mean and quasi-arithmetic mean. Moreover, it does not require any leaning process. Experimental results on three publicly available data sets (i.e. NIST-BSSR1 Multimodal, NIST-BSSR1 Fingerprint and NIST-BSSR1 Face) for multi-modal, multi-unit and multi-algorithm systems show that presented WQAM fusion algorithm outperforms the previously proposed score fusion rules based on transformation (e.g. t-norms), classification (e.g. support vector machines) and density estimation (e.g. likelihood ratio) methods.

show abstract

Multibiometrics Enhancement Using Quality Measurement in Score Level Fusion

Cited by 4 publications

References 18 publications

An Approach for Full Reinforcement-Based Biometric Score Fusion

An Approach for Full Reinforcement-Based Biometric Score Fusion

Score‐level fusion using generalized extreme value distribution and DSmT, for multi‐biometric systems

Weighted quasi‐arithmetic mean based score level fusion for multi‐biometric systems

Contact Info

Product

Resources

About