Multimodal biometric authentication based on deep fusion of electrocardiogram (ECG) and finger vein

Biometric identification depends on the statistical analysis of the unique physical and behavioral characteristics of individuals. However, a unimodal biometric system is susceptible to different attacks such as spoof attacks. To overcome these limitations, we propose a multimodal biometric authentication system based on deep fusion of electrocardiogram (ECG) and finger vein. The proposed system has three main components, which are biometric pre-processing, deep feature extraction, and authentication. During the pre-processing, normalization and filtering techniques are adapted for each biometric. In the feature extraction process, the features are extracted using a proposed deep Convolutional Neural Network (CNN) model. Then, the authentication process is performed on the extracted features using five well-known machine learning classifiers: Support Vector Machine (SVM), K-Nearest Neighbors (KNNs), Random Forest (RF), Naive Bayes (NB), and Artificial Neural Network (ANN). In addition, to represent the deep features in a low-dimensional feature space and speed up the authentication task, we adopt Multi-Canonical Correlation Analysis (MCCA). We combine the two biometric systems based on ECG and finger vein into a single multimodal biometric system using feature and score fusion. The performance of the proposed system is tested on two finger vein (TW finger vein and VeinPolyU finger vein) databases and two ECG (MWM-HIT and ECG-ID) databases. Experimental results reveal improvement in terms of authentication performance with Equal Error Rates (EERs) of 0.12% and 1.40% using feature fusion and score fusion, respectively. Furthermore, the authentication with the proposed multimodal system using MCCA feature fusion with a KNN classifier shows an increase of accuracy by an average of 10% compared with those of other machine learning algorithms. Therefore, the proposed biometric system is effective in performing secure authentication and assisting the stakeholders in making accurate authentication of users.

[1]  Mohamed Hammad,et al.  Ear verification based on a novel local feature extraction , 2017, ICBEA '17.

[2]  Jiankun Hu,et al.  Securing Deep Learning Based Edge Finger Vein Biometrics With Binary Decision Diagram , 2019, IEEE Transactions on Industrial Informatics.

[3]  Shanq-Jang Ruan,et al.  Finger-Vein as a Biometric-Based Authentication , 2019, IEEE Consumer Electronics Magazine.

[4]  Mohamed Hammad,et al.  A novel biometric based on ECG signals and images for human authentication , 2016, Int. Arab J. Inf. Technol..

[5]  Xiaoding Wang,et al.  Enabling Secure Authentication in Industrial IoT With Transfer Learning Empowered Blockchain , 2021, IEEE Transactions on Industrial Informatics.

[6]  Naoto Miura,et al.  Finger-vein authentication based on deformation-tolerant feature-point matching , 2016, Machine Vision and Applications.

[7]  Shan Juan Xie,et al.  An available database for the research of finger vein recognition , 2013, 2013 6th International Congress on Image and Signal Processing (CISP).

[8]  Xu Zhang,et al.  Feature-level fusion of fingerprint and finger-vein for personal identification , 2012, Pattern Recognit. Lett..

[9]  Chengjun Liu,et al.  A shape- and texture-based enhanced Fisher classifier for face recognition , 2001, IEEE Trans. Image Process..

[10]  Ahmed A. Abd El-Latif,et al.  Multimodal biometric authentication based on score level fusion of finger biometrics , 2014 .

[11]  Mohamed Hammad,et al.  Fingerprint classification based on a Q-Gaussian multiclass support vector machine , 2017, ICBEA '17.

[12]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[13]  Gongping Yang,et al.  Sliding Window-Based Region of Interest Extraction for Finger Vein Images , 2013, Sensors.

[14]  Harish Dureja,et al.  Topological Models for Prediction of Pharmacokinetic Parameters of Cephalosporins using Random Forest, Decision Tree and Moving Average Analysis , 2008 .

[15]  Qing Zhang,et al.  Finger Vein Recognition Based on Fusion of Deformation Information , 2020, IEEE Access.

[16]  Ahmed A. Abd El-Latif,et al.  Toward accurate localization and high recognition performance for noisy iris images , 2012, Multimedia Tools and Applications.

[17]  Mohamed Hammad,et al.  Multimodal Biometric Authentication Systems Using Convolution Neural Network Based on Different Level Fusion of ECG and Fingerprint , 2019, IEEE Access.

[18]  José María de Fuentes,et al.  Effect of attacker characterization in ECG-based continuous authentication mechanisms for Internet of Things , 2018, Future Gener. Comput. Syst..

[19]  Edmond S. L. Ho,et al.  A Multitier Deep Learning Model for Arrhythmia Detection , 2020, IEEE Transactions on Instrumentation and Measurement.

[20]  Haibin Shen,et al.  ECG Authentication Method Based on Parallel Multi-Scale One-Dimensional Residual Network With Center and Margin Loss , 2019, IEEE Access.

[21]  Hongxun Yao,et al.  Deep Feature Fusion for VHR Remote Sensing Scene Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Mohamed Hammad,et al.  ResNet‐Attention model for human authentication using ECG signals , 2020, Expert Syst. J. Knowl. Eng..

[23]  Gongping Yang,et al.  Human identification using finger vein and ECG signals , 2019, Neurocomputing.

[24]  Mohamed Hammad,et al.  A novel two-dimensional ECG feature extraction and classification algorithm based on convolution neural network for human authentication , 2019, Future Gener. Comput. Syst..

[25]  Ahmed A. Abd El-Latif,et al.  Finger-vein Verification Using Gabor Filter and SIFT Feature Matching , 2012, 2012 Eighth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[26]  S. Veluchamy,et al.  System for multimodal biometric recognition based on finger knuckle and finger vein using feature-level fusion and k-support vector machine classifier , 2017, IET Biom..

[27]  Ajay Kumar,et al.  Human Identification Using Finger Images , 2012, IEEE Transactions on Image Processing.

[28]  Tao Zhan,et al.  Finger vein biometric verification using block multi-scale uniform local binary pattern features and block two-directional two-dimension principal component analysis , 2020, Optik.

[29]  M. Shamim Hossain,et al.  Edge-centric multimodal authentication system using encrypted biometric templates , 2018, Future Gener. Comput. Syst..

[30]  Mohamed Hammad,et al.  Parallel score fusion of ECG and fingerprint for human authentication based on convolution neural network , 2019, Comput. Secur..

[31]  Ryszard Tadeusiewicz,et al.  Neural Networks In Mining Sciences – General Overview And Some Representative Examples , 2015 .

[32]  Julian Fiérrez,et al.  Multiple classifiers in biometrics. part 1: Fundamentals and review , 2018, Inf. Fusion.

[33]  Vijay Kumar Jha,et al.  Multibiometric fusion strategy and its applications: A review , 2019, Inf. Fusion.

[34]  WADOOD ABDUL,et al.  Biometric Security Through Visual Encryption for Fog Edge Computing , 2017, IEEE Access.

[35]  Khan Muhammad,et al.  Combining Multiple Biometric Traits Using Asymmetric Aggregation Operators for Improved Person Recognition , 2020, Symmetry.

[36]  Ahmed A. Abd El-Latif,et al.  Finger multibiometric cryptosystem based on score-level fusion , 2015, Int. J. Comput. Appl. Technol..

[37]  Feng Jiang,et al.  Very deep feature extraction and fusion for arrhythmias detection , 2018, Neural Computing and Applications.

[38]  Janmenjoy Nayak,et al.  Applications and Advancements of Firefly Algorithm in Classification: An Analytical Perspective , 2020 .

[39]  Yen-Lung Lai,et al.  Finger Vein Template Protection Based on Alignment-Robust Feature Description and Index-of-Maximum Hashing , 2020, IEEE Transactions on Biometrics, Behavior, and Identity Science.

[40]  Mohamed Hammad,et al.  Detection of abnormal heart conditions based on characteristics of ECG signals , 2018, Measurement.

[41]  Ronali Madhusmita Sahoo,et al.  Deep Recurrent Neural Network (Deep-RNN) for Classification of Nonlinear Data , 2020 .

[42]  Qiuxia Wu,et al.  FVRAS-Net: An Embedded Finger-Vein Recognition and AntiSpoofing System Using a Unified CNN , 2020, IEEE Transactions on Instrumentation and Measurement.

[43]  Juan Arteaga-Falconi,et al.  ECG and fingerprint bimodal authentication , 2018, Sustainable Cities and Society.

[44]  Mohamed Abdel-Mottaleb,et al.  Fully automatic face normalization and single sample face recognition in unconstrained environments , 2016, Expert Syst. Appl..

[45]  Janmenjoy Nayak,et al.  A Novel Honey-Bees Mating Optimization Approach with Higher order Neural Network for Classification , 2018, J. Classif..

[46]  Khan Muhammad,et al.  A Novel Deep Transfer Learning Method for Detection of Myocardial Infarction , 2019, ArXiv.

[47]  M. Shamim Hossain,et al.  Score level multibiometrics fusion approach for healthcare , 2017, Cluster Computing.

[48]  Arun Ross,et al.  A Comprehensive Overview of Biometric Fusion , 2019, Inf. Fusion.

[49]  Ahmed A. Abd El-Latif,et al.  An effective preprocessing method for finger vein recognition , 2013, Other Conferences.

[50]  Rizal Setya Perdana,et al.  Combining Likes-Retweet Analysis and Naive Bayes Classifier within Twitter for Sentiment Analysis , 2018 .

[51]  Yuguang Fang,et al.  Practical Privacy-Preserving ECG-Based Authentication for IoT-Based Healthcare , 2019, IEEE Internet of Things Journal.

[52]  Andreas Uhl,et al.  The Two Sides of the Finger - An Evaluation on the Recognition Performance of Dorsal vs. Palmar Finger-Veins , 2018, 2018 International Conference of the Biometrics Special Interest Group (BIOSIG).

[53]  Xiaohong Zhang,et al.  ECG authentication system design incorporating a convolutional neural network and generalized S-Transformation , 2018, Comput. Biol. Medicine.

[54]  Mohamed Hammad,et al.  Cancelable biometric authentication system based on ECG , 2018, Multimedia Tools and Applications.

[55]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[56]  Ahmed A. Abd El-Latif,et al.  Finger Vein Recognition with Gabor Wavelets and Local Binary Patterns , 2013, IEICE Trans. Inf. Syst..

[57]  Ahmed A. Abd El-Latif,et al.  An enhanced thermal face recognition method based on multiscale complex fusion for Gabor coefficients , 2013, Multimedia Tools and Applications.

[58]  Qiong Li,et al.  Frame duplication and shuffling forgery detection technique in surveillance videos based on temporal average and gray level co-occurrence matrix , 2020, Multimedia Tools and Applications.

[59]  Sung Wook Baik,et al.  CNN-based anti-spoofing two-tier multi-factor authentication system , 2019, Pattern Recognit. Lett..

[60]  Ahmed A. Abd El-Latif,et al.  Myocardial infarction detection based on deep neural network on imbalanced data , 2021, Multimedia Systems.

[61]  M. Shamim Hossain,et al.  Verifying the Images Authenticity in Cognitive Internet of Things (CIoT)-Oriented Cyber Physical System , 2017, Mob. Networks Appl..

[62]  Mamun Bin Ibne Reaz,et al.  A novel SVM-kNN-PSO ensemble method for intrusion detection system , 2016, Appl. Soft Comput..

[63]  Ayman El-Sayed,et al.  Iris Recognition Using Multi-Algorithmic Approaches for Cognitive Internet of things (CIoT) Framework , 2018, Future Gener. Comput. Syst..

[64]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[65]  Chun-Chieh Hsiao,et al.  Multiple biometric authentication for personal identity using wearable device , 2016, 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC).