Optimal feature level fusion for secured human authentication in multimodal biometric system

Purohit, Himanshu; Ajmera, Pawan K.

doi:10.1007/s00138-020-01146-6

Cited by 44 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Himanshu Purohit and Pawan K. Ajmera [35] proposed a feature-level fusion technique for multimodal biometric recognition. For optimal selection, this method employs an oppositional gray wolf optimization algorithm and an LQ algorithm.…”

Section: Related Workmentioning

confidence: 99%

A Multimodal Biometric Authentication System Using the Exponential Water Wave Optimization Algorithm

Vensila

Wesley

2022

Preprint

View full text Add to dashboard Cite

The biometric system relies on a single biometric identifier which could not meet the desired performance required for personal identification. Hence, identification based on the multimodal biometric system is emerged in the research community to achieve the personal identification process more effective. Owing to the strong binding among user identity and biometric template, the user privacy is revealed and hence the security resulted in a major requirement in the biometric system. An authentication based multimodal biometric system is developed in this research by considering different modalities, such as fingerprint, finger vein, and face. Here, the bit string is generated from the biometric sample in such a way that the bit strings are fused by employing the proposed Exponential Water Wave Optimization (EWWO) algorithm based on the involvement of logic operations. However, the process of fusion is accomplished in such a way that it depends on the random selection of two logic operators by the developed optimization approach. Accordingly, the developed EWWO is derived by the combination of Exponentially Weighted Moving Average (EWMA) and Water Wave Optimization (WWO) respectively. The authentication mechanism is achieved by employing the biometric template with the encoder and decoder operation. Moreover, the proposed method achieved the performance for Equal Error rate (EER), False Acceptance Rate (FAR), and False Rejection Rate (FRR) with the value of 0.0717, 0.0745, and 0.0689, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

A Multimodal Biometric Authentication System Using the Exponential Water Wave Optimization Algorithm

Vensila

Wesley

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Beta and Delta Gray refer to classes two and three in the specific structure of wolves. In short, they are extra wolves with enough help to set up an alpha or group presentation [31,32]. The remaining wolves represent omega, which is a small group of gray wolves.…”

Section: Pre-processingmentioning

confidence: 99%

Multi-modal biometric fusion based continuous user authentication for E-proctoring using hybrid LCNN-Salp swarm optimization

Purohit

Ajmera

2021

Cluster Comput

Self Cite

View full text Add to dashboard Cite

“…Several researchers have attempted to conduct comparative experiments between several different levels of fusion strategies. In the literature [10], feature-level fusion strategies were compared with score-level fusion strategies and decision-level fusion strategies, it was shown that feature fusion has the potential to exhibit higher accuracy in the early stages between various multimodal features. Since only one classifier is required, feature-level fusion is generally faster than decision-level fusion, which usually uses multiple classifiers [11].…”

Section: Introductionmentioning

confidence: 99%

Multimodal Finger Recognition Based on Asymmetric Networks With Fused Similarity

Huang

Wang

2023

IEEE Access

View full text Add to dashboard Cite

Multimodal biometric system has received increasing interest as it offers a more secure and accurate authentication solution than unimodal systems. However, existing biometric fusion methods are still inadequate in dealing with correlations and redundancy of multimodal features simultaneously, causing bottlenecks in performance improvement. To overcome the above problem, this paper proposes an end-toend multimodal finger recognition model that incorporates attention mechanisms into a similarity-aware encoder to achieve accurate recognition results for accurate identification results. Firstly, due to the different distribution of fingerprint and finger vein images, we propose a finger asymmetric backbone network (FAB-Net) for extracting discriminative intra-modal features, which reduces the network width by efficient utilization of feature maps. Then, a novel attention-based encoder fusion network (AEF-Net) with fused similarity performs dimensionality reduction-based fusion on multimodal multilevel features to alleviate performance degradation due to information redundancy. We also introduce channel attention in AEF-Net, which differs from the traditional attention mechanism by considering interdependencies between modalities to further improve performance. Extensive recognition experiments are conducted on three multimodal finger databases to verify the effectiveness of our method compared to state-of-the-art methods. Detailed ablation studies have also been carried out, which demonstrated that encoder-based reconstruction of redundant information can improve recognition performance.INDEX TERMS Multimodal biometric recognition, feature fusion, autoencoder, deep learning.

show abstract

Optimal feature level fusion for secured human authentication in multimodal biometric system

Cited by 44 publications

References 23 publications

A Multimodal Biometric Authentication System Using the Exponential Water Wave Optimization Algorithm

A Multimodal Biometric Authentication System Using the Exponential Water Wave Optimization Algorithm

Multi-modal biometric fusion based continuous user authentication for E-proctoring using hybrid LCNN-Salp swarm optimization

Multimodal Finger Recognition Based on Asymmetric Networks With Fused Similarity

Contact Info

Product

Resources

About