Soft and hard biometrics fusion for improved identity verification

Zewail, Rami; Elsafi, Ahmed; Saeb, Magdy; Hamdy, N.

doi:10.1109/mwscas.2004.1353967

Cited by 28 publications

(30 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…His experiments showed an improvement of around 1-2% when combining ethnicity and gender traits with fingerprint signals. Other related approaches such as Zewail et al [34] use iris colour (a soft biometric) with fingerprint and iris using a weighted average scheme and a Parzen Classifier. These approaches used automatically extracted soft biometrics from existing video or image signals.…”

Section: Human Descriptions As a Biometricmentioning

confidence: 99%

The Use of Semantic Human Description as a Soft Biometric

Samangooei

Guo

Nixon

2008

2008 IEEE Second International Conference on Biometrics: Theory, Applications and Systems

View full text Add to dashboard Cite

Abstract-Gait as a biometric has a unique advantage that it can be used when images are acquired at a distance and other biometrics are at too low a resolution to be perceived. In such a situation, there is still information which can be readily perceived by human vision, yet is difficult to extract automatically. We examine how this information can be used to enrich the recognition process. We call these descriptions semantic annotations and investigate their use in biometric scenarios. We outline a group of visually assessable physical traits formulated as a mutually exclusive set of semantic terms; we contend that these traits are usable in soft biometric fusion. An experiment to gather semantic annotations was performed and the most reliable traits are identified using ANOVA. We rate the ability to correctly identify subjects using these semantically prescribed traits, both in isolation as well as in fusion with an automatically derived gait signature.

show abstract

Section: Human Descriptions As a Biometricmentioning

confidence: 99%

The Use of Semantic Human Description as a Soft Biometric

Samangooei

Guo

Nixon

2008

2008 IEEE Second International Conference on Biometrics: Theory, Applications and Systems

View full text Add to dashboard Cite

show abstract

“…For improving the security and accuracy of biometric systems, information from multiple biometric sources is integrated into a single multi-biometric system. Such information integration is known as multi-biometric fusion [3]. Multi-biometric authentication systems (MBAS) can be developed a) by integrating several physiological and behavioral traits of an individual, b) using multiple sensor systems, c) using multiple matcher systems and/or d) combining soft and hard biometrics.…”

Section: Integrated Biometric Systemsmentioning

confidence: 99%

“…Zewail et al [3] in 2004 reported a multimodal biometric system in which iris color, a soft biometric, was integrated with the output of a primary biometric system comprising of fingerprint and iris texture as hard biometrics. The frequency and orientation of ridges was captured to provide distinct representations.…”

Section: Previous Work Donementioning

confidence: 99%

Towards an Integrated Biometric Technique

Singhal¹,

Singh²,

Jain³

2012

IJCA

View full text Add to dashboard Cite

A biometric system is basically a pattern recognition system. Biometrics based user authentication system serve as a reliable means for meeting the challenges in today"s world of information and network security. It has gained enormous interest by scientists and researchers. Unimodal biometric systems that employ only a single biometric trait fails to achieve the desired security levels. Even the best unimodal biometric system suffers from various problems. To overcome these issues, we propose a multi-modal biometric system which employs iris and hand-geometry biometric traits. The iris patterns of human eye are very complex and random. It is almost impossible for an imposter to imitate them. Handgeometry measurements are not so distinctive and hence are used only for verification purpose. By combining them with other biometric trait like iris, a more secure multi-biometric security system can be obtained for verification as well as identification purpose. In this paper we will present a brief introduction about unimodal biometric systems, need for biometrics integration, various integration levels, types of multi-biometric systems and some previous research work. In the last section (7 th ), we have presented our proposed multibiometric system.

show abstract

“…This system was quickly superseded by other forms of forensic analysis such as fingerprints. More recently, description of anthropometric traits have been used along side primary biometrics in soft biometric fusion to improve recognition rates [18,28,41,44]. Jain et al [17] present an example where, using a general bayesian framework, they fuse fingerprints with the soft features of gender, ethnicity and height, achieving improved identification rates.…”

Section: Semantic Biometricsmentioning

confidence: 99%