Feature Level Fusion of Multimodal Biometrics and Two Tier Security in ATM System

Geethanjali, N.; Thamaraiselvi, K.

doi:10.5120/12030-8041

Cited by 11 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Geetanjali and Thamaraiselvi (2013), a multimodal biometric system is suggested having faced, iris and fingerprint as biometric modalities. A two level security is proposed for an ATM system.…”

Section: Multimodal Biometric Cryptosystemmentioning

confidence: 99%

Multimodal biometric cryptosystem based on fusion of wavelet and curvelet features in robust security application

Inamdar¹,

Dandawate²

2016

IJBM

View full text Add to dashboard Cite

The authentication system used at the automated teller machines (ATM) is a unique personal identification number (PIN). This PIN can be easily tapped and misused. In this paper we propose a method in which the PIN is replaced by the biometrics of the individual to have a more secure transaction. A complete hardware system is designed to capture the biometric traits such as face, fingerprint and palm vein. The captured images are pre-processed and then features are extracted which are then fused at feature level. Cryptography is applied on the fused feature vector. Matching is performed using Euclidean distance at the server end. Palm vein is particularly chosen as a biometric trait along with widely used face and fingerprint because it is unique and is impossible to forge the vein pattern of an individual. Curvelet and Wavelet Transforms are used for the feature extraction. Experimental results indicate a good level of security and recognition rate of 91% and 89% is achieved on our own generated database. The results are promising when compared with other existing similar techniques.Reference to this paper should be made as follows: Inamdar, S.R. and Dandawate, Y.H. (2016) 'Multimodal biometric cryptosystem based on fusion of wavelet and curvelet features in robust security application', Int. He has 23 years of teaching experience and has published more than 55 papers 34 S.R. Inamdar and Y.H. Dandawate in reputed international and national conferences/referred journals. His areas of interest are in signal and image processing, embedded systems and soft computing. He is a reviewer and editorial board member of reputed journals in India and abroad. He is also working on several research projects. He is a senior member of IEEE and Fellow member of IETE, India.

show abstract

Section: Multimodal Biometric Cryptosystemmentioning

confidence: 99%

Multimodal biometric cryptosystem based on fusion of wavelet and curvelet features in robust security application

Inamdar¹,

Dandawate²

2016

IJBM

View full text Add to dashboard Cite

show abstract

“…During verification, the biometric of the user is matched to the vault and only a sufficient match of the minutiae points reveals the secret to unlock the vault. Geethanjali et al [61] presented the variance amongst fuzzy vault and fuzzy commitment, they pointed that biometric traits secured by fuzzy commitment are symbolized in the practice of binary vectors which are distributed into a sum of sections and each section is independently secured. The biometric traits in fuzzy vault are symbolized in the form of point set which is protected by hiding them with chaff points.…”

Section: Biometric Template Protection Techniquesmentioning

confidence: 99%

Assessment of vulnerabilities of the biometric template protection mechanism

Habibu¹,

Sam²

2018

IJATEE

View full text Add to dashboard Cite

In the ever-changing world of global data transmission, the security of data and individual privacy are the growing fears in today's human life worldwide. The major concerns are the protection of the biometric templates in the biometric identification and authentication process. Storage of the biometric template in the database raises the chance of compromising it, hence lead to serious threats and abuse of the person's identity. When an individual's registered biometric data is disclosed, their security and privacy can be compromised. Therefore, public acceptance of biometrics will depend on the system designer's ability to demonstrate that the systems are robust, with low error rates, and tamper proof. If someone's biometric template inside the database is compromised, that consequently might imply identification robbery of that individual. In the recent past, a considerable number of methods for biometric template protection have been published. This article explains, a thorough valuation on numerous attacks and threats associated with the biometric system alongside the biometric template protection, elucidating the measures anticipated to address the threats, to the performance gap and establish the status quo of the current biometric template protection for public acceptance.

show abstract

“…It involves the fusion of two or more biometrics such as fingerprint, facial recognition, iris scanning, hand geometry, signature verification or speech recognition. Multibiometrics is more advantageous over unibiometrics as it is resilience to spoofing and has a low False Acceptance Rate [2].Feature Level Fusion of the proposed biometric traits namely Fingerprint, Iris and Finger vein is carried out on the single secure sketch with Fuzzy Vault and Fuzzy Commitment Cryptosystems. This existing Fuzzy Logic has the limitations of non-revocability, cross matching and brute force attack [6].In order to overcome the above limitations of Fuzzy Logic, Hard Fuzzy logic is proposed.…”

Section: Introductionmentioning

confidence: 99%

“…detailed analysis of the trade-off between matching accuracy and security in the proposed multibiometric cryptosystems is done each containing the three most popular biometric modalities namely fingerprint, iris and face. N. Geethanjali, K. Thamaraiselvi and R. Priyadharshini [2] developed a system to provide a security to the biometric template by generating a secure sketch by making use of multibiometric cryptosystem and which is stored in a database. Feature level fusion is used to combine the features securely which is used in distributed applications like e-commerce, e-banking and ATM.…”

Section: Introductionmentioning

confidence: 99%