Face and ECG Based Multi-Modal Biometric Authentication

Multimodal biometric system for ECG, ear and iris recognition based on local descriptors

“…Different measures have been calculated to evaluate the performance of our unimodal system. [12] ECG and face decision 99.5 ---Al.hamdani et al [1] ECG and speech score -0.7 --Barra et al [6] ECG and EEG score 96.79 0.956 --Tahmasebi et al [23] Ear, Palmprint and signature rank 99.63 0.37 0.17 0.37 Chakraborty et al [13] ECG and Face feature 97. Local descriptors textures, 1D-LBP, Shifted-1D-LBP and 1D-MR-LBP, extract rich and complex non-fiducial information from the segmented heartbeats.…”

“…In order to improve on the accuracy and reliability of other rank fusion methods, they also suggested a new Markov chain approach for fusing rank information in a multimodal biometric system. Using different rules (the min rule, max rule, product rule and sum rule) in decision level fusion, ECG features extracted via KPCA (Kernel Principal Component Analysis) and face features extracted using Principal Component Analysis (PCA) and Spectral Regression (SR) algorithms are combined to treat the problem of combining different biometric modalities in intelligent video surveillance systems [12],. An implementation of a multimodal system by Al Hamdani et al [1], combined three modalities using score level fusion to reach a higher security level.…”

“…In this paper, new fusion approach of three modalities namely ECG, ear and iris was proposed in an attempt to develop a secure and robust multimodal biometric recognition system. The proposed modalities (ECG, ear or iris) used in the proposed approach was fused with other biometric modalities in many researches [1,12,22,35,38,50] but there is no system fuses the three biometric modalities together.…”

Biometric analysis using fused feature set from side face texture and electrocardiogram

“…Initial effort to fuse face and ECG based features for person identification is reported in [27]. Few more fusion algorithms for biometric authentication are also reported in literature [28, 29]. Generally, these algorithms are based on statistical rules.…”

Algorithms for Processing Biometric Data Oriented to Privacy Protection and Preservation of Significant Parameters

“…The transformation of the outcomes, received at the enrollment stage, to a published part of the secret is also viewed as wrapping in a number of applications where the unwrapping is possible only when outcomes, received at the verification stage, are close to the wrapped data [14]. The use of possibly non-stationary probability distributions also allows us to include multi-biometric measurements (see, for example [15], [16]) into the processing. Furthermore, the addressed issues are relevant to constructing fault-tolerant passwords from biometric data [17]- [19].…”