Transforming Finger Vein Template in Multi-instance Scenario

Citation

Cai, Shuxian and Yau, Wei Chuen and Ong, Thian Song and Teng, Jackson Horlick (2022) Transforming Finger Vein Template in Multi-instance Scenario. In: 2022 10th International Conference on Information and Communication Technology (ICoICT), 2-3 August 2022, Bandung, Indonesia.

[img] Text
11.pdf - Published Version
Restricted to Repository staff only

Download (675kB)

Abstract

Unlike single biometric systems, multi-instance biometric systems can reduce the risk of user privacy leakage. Meanwhile, maintaining biometric security also requires template protection. However, there is still limited study focusing on template protection in multi-instance biometrics. To address such issues, this paper proposes a method for multiinstance finger vein template protection. In this work, the vein features of different finger instances are extracted at feature fusion and image fusion levels using Gabor filter method, respectively. For feature transformation, the Gabor feature blocks are transformed with Bloom filters to extract the finger vein template for secure storage and verification. When analyzing the performance, the experiments are mainly conducted with the constant key scenario to be compared with performance of the baseline Gabor feature extraction method and the genuine key scenario. It is shown that this proposed method effectively improves system performance, with equal error rate (EER) as low as 5.00% in constant key scenario, while maintaining zero error rate in genuine key scenario. Besides, the proposed method is also examined for the properties of unlinkability and irreversibility as required for a template protection method.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Finger vein, Fingerprint multi-instance, template protection, Bloom filter
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800-8360 Electronics > TK7871 Electronics--Materials
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 05 Jan 2023 01:22
Last Modified: 05 Jan 2023 01:22
URII: http://shdl.mmu.edu.my/id/eprint/10749

Downloads

Downloads per month over past year

View ItemEdit (login required)