Fusing multimodal biometrics with quality estimates via a Bayesian belief network

Maurer, Donald E.; Baker, John P.

doi:10.1016/j.patcog.2007.08.008

Cited by 56 publications

(36 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such results have been achieved using a variety of fusion techniques. Donald E. Maurer and John P. Baker et al [12] have presented fusion architecture based on Bayesian belief networks. Minutiae feature extraction method for fingerprint images give better results than any other feature extraction algorithm.…”

Section: Literature Surveymentioning

confidence: 99%

Adaptive Cascade Classifier based Multimodal Biometric Recognition and Identification System

Gawande¹,

Hajari²

2013

IJAIS

View full text Add to dashboard Cite

Biometrics consists of techniques for uniquely recognizing humans based upon one or more intrinsic physical or behavioral traits such as Iris, fingerprint, Face and Palm geometry etc. To overcome the limitations of Unimodal biometric system, a multimodal biometric is proposed. Amongst the various fusion levels, feature level fusion is expected to offer better recognition. Feature level fusion fused the extracted feature obtained from biometric traits. The proposed system is based on feature level fusion and adaptive cascade classifier for precise and reliable multimodal recognition and identification. Verification of Genuine and imposter individual classification is done using Backpropagation neural network. The simulation results demonstrated that a multibiometric template provides better recognition performance compared to a unibiometric template and adaptive cascade classification system significantly outperforms single classifier. General TermsAdaptive Cascade Classifier, Feature level fusion.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Adaptive Cascade Classifier based Multimodal Biometric Recognition and Identification System

Gawande¹,

Hajari²

2013

IJAIS

View full text Add to dashboard Cite

show abstract

“…It assumes value equal to '0' when the samples belong to the Genuine class and '1' when the samples belong to the Impostor class. The variable m denotes the match score between the two samples (e.g., gallery and probe) whose value is affected by the state of the variable I [15], [4]. For example, a match score between two samples of different individuals (I=1) is likely to be lower than that of samples com-ing from the same individual (I=0).…”

Section: Bayesian Belief Network Frameworkmentioning

confidence: 99%

Combining match scores with liveness values in a fingerprint verification system

Marasco

Ding

Ross

2012

2012 IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS)

View full text Add to dashboard Cite

“…For each recognition tasks, the effectiveness of the presented GPP has been proved using experimentation. Donald E. Maurer and John P. Baker et al [28] have described fusion architecture on the basis of Bayesian belief networks. The proposed technique utilized the graphical structure of Bayes nets to define and certainly model statistical dependencies among significant variables: per sample measurements such as, match scores and consequent quality estimates and global decision variables.…”

Section: Review Of Related Literaturementioning

confidence: 99%

Cryptographic Key Generation from Multiple Biometric Modalities: Fusing Minutiae with Iris Feature

Jagadeesan¹,

Thillaikkarasi²,

Duraiswamy³

2010

IJCA

View full text Add to dashboard Cite

Human users find difficult to remember long cryptographic keys. Therefore, researchers, for a long time period, have been investigating ways to use biometric features of the user rather than memorable password or passphrase, in an attempt to produce tough and repeatable cryptographic keys. Our goal is to integrate the volatility of the user's biometric features into the generated key, so as to construct the key unpredictable to a hacker who is deficient of important knowledge about the user's biometrics. In our earlier research, we have incorporated multiple biometric modalities into the cryptographic key generation to provide better security. In this paper, we propose an efficient approach based on multimodal biometrics (Iris and fingerprint) for generating a secure cryptographic key, where the security is further enhanced with the difficulty of factoring large numbers. At first, the features, minutiae points and texture properties are extracted from the fingerprint and iris images respectively. Then, the extracted features are fused at the feature level to obtain the multi-biometric template. Finally, a multi-biometric template is used for generating a 256-bit cryptographic key. For experimentation, we have used the fingerprint images obtained from publicly available sources and the iris images from CASIA Iris Database. The experimental results have showed that the generated 256-bit cryptographic key is capable of providing better user authentication and better security.

show abstract

Fusing multimodal biometrics with quality estimates via a Bayesian belief network

Cited by 56 publications

References 15 publications

Adaptive Cascade Classifier based Multimodal Biometric Recognition and Identification System

Adaptive Cascade Classifier based Multimodal Biometric Recognition and Identification System

Combining match scores with liveness values in a fingerprint verification system

Cryptographic Key Generation from Multiple Biometric Modalities: Fusing Minutiae with Iris Feature

Contact Info

Product

Resources

About