Multimodal Biometric Person Authentication Using Face, Ear and Periocular Region Based on Convolution Neural Networks

Biometrics is an active area of research because of the increase in need for accurate person identification in numerous applications ranging from entertainment to security. Unimodal and multimodal are the well-known biometric methods. Unimodal biometrics uses one biometric modality of a person for person identification. The performance of an unimodal biometric system is degraded due to certain limitations such as: intra-class variations and nonuniversality. The person identification using more than one biometric modality of a person is multimodal biometrics. This method of identification has gained more interest due to resistance on spoof attacks and more recognition rate. Conventional methods of feature extraction have difficulty in engineering features that are liable to more variations such as illumination, pose and age variations. Feature extraction using convolution neural network (CNN) can overcome these difficulties because large dataset with robust variations can be used for training, where CNN can learn these variations. In this paper, we propose multimodal biometrics at feature level horizontal fusion using face, ear and periocular region biometric modalities and apply deep learning CNN for feature representation and also we propose face, ear and periocular region dataset that are robust to intra-class variations. The evaluation of the system is made by using proposed database. Accuracy, Precision, Recall and [Formula: see text] score are calculated to evaluate the performance of the system and had shown remarkable improvement over existing biometric system.

Evaluating the Performance of Speaker Recognition Solutions in E-Commerce Applications

Two important tasks in many e-commerce applications are identity verification of the user accessing the system and determining the level of rights that the user has for accessing and manipulating system’s resources. The performance of these tasks is directly dependent on the certainty of establishing the identity of the user. The main research focus of this paper is user identity verification approach based on voice recognition techniques. The paper presents research results connected to the usage of open-source speaker recognition technologies in e-commerce applications with an emphasis on evaluating the performance of the algorithms they use. Four open-source speaker recognition solutions (SPEAR, MARF, ALIZE, and HTK) have been evaluated in cases of mismatched conditions during training and recognition phases. In practice, mismatched conditions are influenced by various lengths of spoken sentences, different types of recording devices, and the usage of different languages in training and recognition phases. All tests conducted in this research were performed in laboratory conditions using the specially designed framework for multimodal biometrics. The obtained results show consistency with the findings of recent research which proves that i-vectors and solutions based on probabilistic linear discriminant analysis (PLDA) continue to be the dominant speaker recognition approaches for text-independent tasks.

Cancelable Multimodal Biometrics Based on Chaotic Maps

Biometric authentication systems raise certain concerns with regard to security, violation of privacy, and storage issues of biometric templates. This paper proposes a protection approach of biometric templates storage in a multimodal biometric system while ensuring both the cancelability of biometric templates and the efficiency of the authentication process. We propose applying a chaotic maps-based transform on the biometric features to address the cancelability issue. We used Logistic map and Torus Automorphism to generate cancelable biometric features of the face and fingerprint minutia points, respectively. Both transformed features would be concatenated and saved in the database of the system instead of the original features. In the authentication stage, the similarity scores of both transformed face and fingerprint templates are computed and fused using the weighted sum rule. The results of the experimentation, conducted using images from the ORL face and FVC2002 DB1 fingerprint databases, demonstrated the higher performance of the proposed approach achieving a genuine accept rate equal to 100%. Moreover, the obtained results confirmed the soundness of the proposed cancelable technique to satisfy the biometric systems’ requirements (i.e., security, revocability, and diversity).

Comparison of levels and fusion approaches for multimodal biometrics

The biometric-based authentication system occupies maximal space in the field of security administration. Biometric applications are swiftly accelerating in day-to-day life such as computer login, smart homes, online banking, hospitals, border areas, industries, forensics, e-voting attendance system and investigation of crime. A reliable and accurate recognition body can be achieved with multimodal biometric methodologies. In this paper, we discuss starting with an introduction to biometric systems followed by their classification, and advantages as well as disadvantages. In today’s world, most of the systems are unimodal biometrics having a lot of limitations to overcome those multimodal biometrics comes in to picture. In this paper we have discussed comprehensive representation on the system of multimodal biometric, various modes of undertakings, the significance of information fusion, a different section is allotted on the various possible levels of fusion involving sensor-level, feature-level, score-level, and decision -level as well as different rules of fusion.