A low-cost multimodal biometric sensor to capture finger vein and fingerprint

Abstract

Multimodal biometric systems based on fingerprint and finger vein modality provide promising features useful for robust and reliable identity verification. In this paper, we present a robust imaging device that can capture both fingerprint and finger vein simultaneously. The presented low-cost sensor employs a single camera followed by both near infrared and visible light sources organized along with the physical structures to capture good quality finger vein and fingerprint samples. We further present a novel finger vein recognition algorithm that explores both the maximum curvature method and Spectral Minutiae Representation (SMR). Extensive experiments are carried out on our newly collected database that comprises of 1500 samples of fingerprint and finger vein from 150 unique fingers corresponding to 41 subjects. Our results demonstrate the efficacy of the proposed sensor with a lowest Equal Error Rate of 0.78%.

Finger vein liveness detection using motion magnification

“…We first present the vulnerability study on our GUC finger vein sensor [7] to 2 different kinds of finger vein print artefacts. The main goal of this vulnerability study is to obtain the Spoof False Acceptance Rate (SFAR%) that indicates the applicability of the artefact samples collected in this work to spoof the sensor.…”

An efficient finger vein indexing scheme based on unsupervised clustering

“…Table 3 also indicates the results with different number of clusters (K). In order to present the comprehensive comparison of the proposed feature extraction scheme we compare the results with most recent finger vein feature extraction scheme based on the improved Spectral Minutiae Representation (SMR) [13]. We particularly choose the SMR as it is most recent method that have demonstrated good performance and also provide the real number features that will fit well to our proposed indexing framework.…”

“…In the next step, we fix the ROI by discarding 40 pixels on either side of the finger starting from U c (x, y) and L c (x, y). Finally ROI is corrected for the translation and rotation using affine transform as mentioned in [13]. Figure 3 shows the ROI extraction from different databases adopted in this work.…”

“…This enables the adaptation of the finger vein biometric based identification solution in a wide range of banking application especially in the Asian counties. The finger vein biometrics has received remarkable progress from recent decades that resulted in various feature extraction schemes that mainly includes Maximum Curvature points (MCP) [8], Wide Line Detector (WLD) [3], Repeated Line Tracking (RLT) [7], Spectral Minutiae Representation (SMR) [2] and improved Spectral Minutiae Representation [13]. These feature extraction schemes have demonstrated very good accuracy in building a ginger vein based identification solution.…”

Finger vascular pattern imaging — A comprehensive evaluation

“…The complexity of the challenge increases again due to varying thickness of finger making the light not to be distributed uniformly. These challenges were overcome by a recently proposed vein sensor which has demonstrated superior quality imaging [14].…”