Next Article in Journal
p-STFT: A Robust Parameter Estimator of a Frequency Hopping Signal for Impulsive Noise
Previous Article in Journal
Analytical Solution of Fractional-Order Hyperbolic Telegraph Equation, Using Natural Transform Decomposition Method
Open AccessArticle

Detecting Fake Finger-Vein Data Using Remote Photoplethysmography

1
Department of Computer Science, Graduate School, Sangmyung University, Hongjimun 2-Gil 20, Jongno-Gu, Seoul 03016, Korea
2
Department of Intelligent Engineering Informatics for Human, Sangmyung University, Hongjimun 2-Gil 20, Jongno-Gu, Seoul 03016, Korea
*
Author to whom correspondence should be addressed.
Electronics 2019, 8(9), 1016; https://doi.org/10.3390/electronics8091016
Received: 16 August 2019 / Revised: 3 September 2019 / Accepted: 9 September 2019 / Published: 11 September 2019
(This article belongs to the Section Bioelectronics)
Today, biometrics is being widely used in various fields. Finger-vein is a type of biometric information and is based on finger-vein patterns unique to each individual. Various spoofing attacks have recently become a threat to biometric systems. A spoofing attack is defined as an unauthorized user attempting to deceive a system by presenting fake samples of registered biometric information. Generally, finger-vein recognition, using blood vessel characteristics inside the skin, is known to be more difficult when producing counterfeit samples than other biometrics, but several spoofing attacks have still been reported. To prevent spoofing attacks, conventional finger-vein recognition systems mainly use the difference in texture information between real and fake images, but such information may appear different depending on the camera. Therefore, we propose a method that can detect forged finger-vein independently of a camera by using remote photoplethysmography. Our main idea is to get the vital sign of arterial blood flow, a biometric measure indicating life. In this paper, we selected the frequency spectrum of time domain signal obtained from a video, as the feature, and then classified data as real or fake using the support vector machine classifier. Consequently, the accuracy of the experimental result was about 96.46%. View Full-Text
Keywords: biometrics; finger-vein; spoofing attacks; photoplethysmography; vital sign biometrics; finger-vein; spoofing attacks; photoplethysmography; vital sign
Show Figures

Figure 1

MDPI and ACS Style

Bok, J.Y.; Suh, K.H.; Lee, E.C. Detecting Fake Finger-Vein Data Using Remote Photoplethysmography. Electronics 2019, 8, 1016.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map

1
Back to TopTop