Fusion of Face and Fingerprint for Robust Personal Verification System

Hassan, Norsalina; Ramli, Dzati Athiar; Suandi, Shahrel Azmin

doi:10.7763/ijmlc.2014.v4.439

Cited by 11 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chaudhary, and Sheetal, et al [10] FpVTE 2003 was analysis to performance and calculated the efficiency of proposed method, fingerprint verification and identification systems. Its summary and analysis report Meva et al, [11] and NIST Biometric and Evaluation and Development paper by Hassan, Norsalina, and Dzati Athiar Ramli et al, [12], Dandawate, and Yogesh H et al [13] and W. Yang, integrated information presented by two fingers at the match score level by probability proportion calculated nonparametric statistical estimates. It was found that multiple fingers improve the verification performance by 4%.…”

Section: \ Fig1 Block Diagram For Multimodal Fusion Methodsmentioning

confidence: 99%

Robust Iris and Fingerprint Biometric Fusion in Multimodal Feature Template Matching

Vijayakumar.¹,

K²

2019

IJRTE

View full text Add to dashboard Cite

Abstract: A fusion scheme in multimodal biometric system is proposed in the name of Multimodal Feature Template Matching (MTM) system derived from the two picture fused values of average point and weighted assessment point. The main objective of MTM algorithm is to design the average point fusion and weighted average point by fusion of Iris and fingerprint features. The MTM algorithm is assigned with avgweights based on their verification accuracy. A hybrid approach of combining biometric image level information id presented. The raw information is merged at image level. This integration addressed, provides a small template and resilience to attacks. However it does not improve the recognition performance, but the performances is also less combination to its unimodal counterpart. Confidence level integration of compatible features of two different uncorrelated biometric traits fingerprint and iris provides sustainable improvement in performance accuracy compared to other integration methods as well as best unimodal system. Fingerprint and iris integrationapproaches presented in this proposed are more robust and reliable.

show abstract

Section: \ Fig1 Block Diagram For Multimodal Fusion Methodsmentioning

confidence: 99%

Robust Iris and Fingerprint Biometric Fusion in Multimodal Feature Template Matching

Vijayakumar.¹,

K²

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…were 310, 301, 290, 283, 271 lx, respectively. For evaluating the verification accuracy, the following values: GAR, FRR, FAR, and ERR [34] were calculated in percentage from the experimental results and shown in Table 4. Note that GAR and ERR are calculated from 1 -FRR, and an average of FRR and FAR, respectively.…”

Section: Performancementioning

confidence: 99%

An Access Control System using RFID and Face Verification with QR Code-based Enrollment

2023

j.it

View full text Add to dashboard Cite

The objective of this paper is to propose the system architecture and implementation of an access control system using RFID technology and face verification. The implemented system was employed to control user's access at the tripod turnstile gate in the library of the Prince of Songkla University (Trang Campus). The access control system is divided into two parts: enrolment and access control. In the enrolment part, the system obtains the user information from three processes:(1) the basic user information (e.g., full name and university identification number) is received via a SOAP web service,(2) the face image of a user is detected by using the camera of a mobile phone, (3) the UID data of a RFID card is read in a form of QR code by using our enrolment board.In the access control part, the RFID reader board forwards the UID data reading from an RFID card into the main controller board via RS-232 communication. The main controller board is used to send the UID data into the Flask web server in order to retrieve the corresponding face image encoding, and then verify with faces that are detected from the webcam at the tripod turnstile gate. The main controller board also controls the tripod turnstile gate via the push-pull solenoid and receives external signals from the proximity sensor and limit switch. The performance of the implemented system using the Raspberry Pi 4 Model B board as the main controller board in terms of verification accuracy and response time was measured, and also compared with the NVIDIA Jetson Nano board.

show abstract

“…Fusing occurs following the fusion of personal features after matching fusion. This comprises the following fusion levels: rank level fusion, match decision level fusion, and score level fusion that can gives good accuracy between 92 and 96%, for more information details you can find it in [9][10][11][12][13][14][15][16][17].…”

Section: Related Wordmentioning

confidence: 99%

Performance of Multimodal Biometric Systems Using Face and Fingerprints (Short Survey)

Abdul-Al

Kyeremeh

Parchin

et al. 2021

2021 IEEE 26th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)

View full text Add to dashboard Cite

Biometric authentication is the science and engineering of assessing and evaluating bioinformatics from the human body in order to increase system security by providing reliable and accurate behaviors and classifiers for personal identification and authentication. Its solutions are widely used in industries, governments, and the military. This paper reviews the multimodal biometric systems that integrated both faces and fingerprints as well as shows which one has the best accuracy and hardware complexity with the methods and databases. Several methods have been used in multimodal biometric systems such as KNN (K-Nearest Neighbor), CNN (Convolutional Neural Network), PCA (Principal Component Analysis), and so on. A multimodal biometric system for face and fingerprints that uses an FoM (Figure of Merit) to compare and show between the articles the best accuracy that have used multimodal biometric system face and fingerprints methods. The best performance has been found is 99.43% by using the cascade multimodal method.

show abstract

Fusion of Face and Fingerprint for Robust Personal Verification System

Cited by 11 publications

References 8 publications

Robust Iris and Fingerprint Biometric Fusion in Multimodal Feature Template Matching

Robust Iris and Fingerprint Biometric Fusion in Multimodal Feature Template Matching

An Access Control System using RFID and Face Verification with QR Code-based Enrollment

Performance of Multimodal Biometric Systems Using Face and Fingerprints (Short Survey)

Contact Info

Product

Resources

About