A hybrid fusion model of iris, palm vein and finger vein for multi-biometric recognition system
- PDF / 2,656,166 Bytes
- 22 Pages / 439.642 x 666.49 pts Page_size
- 49 Downloads / 265 Views
A hybrid fusion model of iris, palm vein and finger vein for multi-biometric recognition system Chenyi Zhou1 · Jing Huang1 · Feng Yang1 · Yaqin Liu1 Received: 25 April 2019 / Revised: 3 March 2020 / Accepted: 30 March 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Biometric system has been widely adopted for human verification or identification, so inherently it requires the characteristics like high security, accuracy and acceptability. However, most of existing unimodal biometric systems provide low-middle security and are vulnerable to attacks. Therefore, multimodal biometric system fuses information from multiple modalities to break these limitations. This paper presents a novel hybrid fusion model for a multimodal biometric system. The hybrid fusion model includes an improved feature fusion algorithm and a novel weighting vote strategy. It captures canonical characteristics with multi-set structure and utilizes score distribution information to help guiding decisionmaking. The system was examined on databases from CASIA, PolyU and SDU respectively, which provided high precision and strong robustness over previous work. Experimental results showed that the proposed approach achieved an average accuracy of 99.33%, which outperformed other fusion strategies in multimodal biometric systems. Keywords Multimodal biometrics · Feature fusion · Decision fusion · Weighting factor · DCA
1 Introduction Considered as a comparatively mature technology, biometrics have already been applied in multimedia application fields: such as access control, financial accounts and E-healthcare systems [19, 30]. The characteristics of an individual, like face [10, 45], fingerprint [24, 49, 50], iris [5] and gait [4, 57], can be used in the biometric identification system. However, with the development of fraud technologies, a single trait of an individual sometimes could be vulnerable to spoofing attacks [35, 42]. Studies have also demonstrated that using a single biometric source for personal identification could be unreliable because they could be easily polluted by the same noise source [9, 33]. In addition, unimodal biometric can not satisfy all the requirements of practical application [8]. Multimodal biometric system Jing Huang
[email protected] 1
Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou, Guangdong Province, China
Multimedia Tools and Applications
integrates two or more different biometric characteristics. It has the capability to break through the limitations of unimodal system by adopting fusion technologies. Firstly, the difficulty of forging multi-biometrics simultaneously prevents fraudulent technologies [25]. Moreover, multi-biometric system contains different kinds of biometrics, this kind of system is insensitive to noise [11]. Simultaneously, it enables the human identification to operate under different circumstances [12, 23]. In the multi-biometric recognition system, fusion str
Data Loading...
