Multimodal Authentication Research Articles

A multimodal authentication for biometric recognition system using hybrid fusion techniques

Biometric Recognition and authentication is used in every application for the secured identification of the persons. Several Researches has been carried out in the past decade that concerns only to enhance the accuracy of biometric algorithms for various kinds of features by ignoring the aspects of robustness and reliability. With this objective, new algorithm called effective linear scale authentication has been proposed which works on the principle of hybrid fusion of two feature inputs such as Hand geometry and iris of the users. The two different techniques have been adopted for the Feature Extraction. One is effective linear binary patterns and other is scale invariant fourier transform and it is stored in the databases for the further verification. This algorithm has been tested with the CASIA Image Datasets and the results had clearly proven that the novel idea of fusing the local features to address the scalar and angular inefficiencies of the existing methods.

Kinect User Authentication using Multimodal Biometric

Objectives: Facial Recognition system has been the most popular non-intrusive authentication system. The proposed system offers to improve the accuracy of facial recognition using multimodal authentication with a 3d depth sensor. Methods/Statistical Analysis: To increase the reliability and robust of the system, we superimpose skeletal biometric features with facial features where data combined using 3D Imaging Technology. Statistical approaches are used for feature transformation using PCA and LDA Algorithm. Findings: To evaluate the system, we collected nearly 1000 individuals with two samples for each, captured in indoor environments under various light effects. The accuracy of the system is built with 95% confidence interval and based on a classifier, three performance curves Receiver Operating Characteristics (ROC), Cumulative Match Score Curves (CMC) and Expected Performance Curves (EPC) are used for performance evaluation. The FRR of the proposed multimodal fusion approach is 0.12 at 0.001 minimal FAR with 95% accuracy. Applications/Improvements: Multimodal biometric is required for strong authentication for the surveillance of smart home, cities and health care sectors where security plays a vital role. This fusion technique improves the reliability, latency, and accuracy of the system in recognizing and authenticating the user. Keywords: 3D Imaging Technology, Face Features, Multimodal Authentication, Skeletal Biometric

Managing distributed trust relationships for multi-modal authentication

Multi-modal active authentication schemes fuse decisions of multiple behavioral biometrics (behaviometrics) to reduce identity verification errors. The challenge that we address in this work is the security risk caused by these decision fusion schemes making invalid assumptions, such as a fixed probability of (in)correct recognition and a temporal congruence of behaviometrics. To mitigate this risk, this paper presents a formal trust model that drives the behaviometric selection and composition. Our trust model adopts a hybrid approach combining policy and reputation based knowledge representation techniques. Our model and framework (1) externalizes trust knowledge from the authentication logic to achieve loosely coupled trust management, and (2) formalizes this knowledge in description logic to reason upon and broker complex distributed trust relationships to make risk-adaptive decisions for multi-modal authentication. The evaluation of our proof-of-concept illustrates an acceptable performance overhead while lifting the burden of manual trust and behaviometric management for multi-modal authentication.

Student Facial Authentication Model based on OpenCV’s Object Detection Method and QR Code for Zambian Higher Institutions of Learning

Facial biometrics captures human facial physiological data, converts it into a data item variable so that this stored variable may be used to provide information security services, such as authentication, integrity management or identification that grants privileged access or control to the owner of that data variable. In this paper, we propose a model for student authentication based on facial biometrics. We recommend a secure model that can be used in the authentication and management of student information in the registration and access of resources, such as bursaries, student accommodation and library facilities at the University of Zambia. Since the model is based on biometrics, a baseline study was carried out to collect data from the general public, government entities, commercial banks, students, ICT regulators and schools on their understanding, use and acceptance of biometrics as an authentication tool. Factor analysis has been used to analyze the findings. The study establishes that performance expectancy, effort expectancy, social influence and user privacy are key determinants for application of a biometric multimode authentication. The study further demonstrates that education and work experience are regulating factors on acceptance and expectancy of a biometric authentication system. Based on these results, we then developed a biometric model that can be used to perform authentication for students in higher learning institutions in Zambia. The results of our proposed model show 66% acceptance rate using OpenCV.

Real-Time Multimodal Biometric User Authentication for Web Application Access in Wireless LAN

Web applications store trustworthy information and can be accessed online through wired or wireless network. Authentication is one of the major challenges to access these web applications. With varying level of sensitive data stored in web application, the concept of level of authentication can be introduced using biometric traits. This paper proposes biometric-based multi-modal authentication system with four levels of securities. Level 1 uses user name and password only; Level 2 uses fingerprint with user name and password; Level 3 uses fingerprint and face with user name and password; Level 4 uses fingerprint, face and iris with user name and password.

A Study on Enhancing Mobile Banking Services using Location based Authentication

Every now and then mobile users are increasing in exponentially all over the world, which leads to the growth of mobile-enabled services like mobile banking. The smart phone now available in the market having the ability to do all the functions that people can do olden days using their personal computers. The introduction of mobile communication technology modernization, innovation and globalization are increasingly driving the banking services to become ubiquitous, personalized, convenience, disseminative and secured. Mobile Banking Authentication has evolved over time to include several parameters such as Biometric, Location, Context, History, Profile etc. In this paper, we discuss new mobile banking services like Digital deposit apps, advanced bill payment apps, and Electronic meeting for mini loan services and Mobile payment apps. We can provide higher security for these new services through an intelligent multi-modal Authentication with Location Awareness. Here the location, where the mobile banking transaction has been executed is captured giving the additional option for a Bank to verify if the transaction has been executed normally or if the parameters are at variance with normal practice. If the Location happens to be very in a different country, an additional verification process can be introduced adding to the entropy of Authentication. If the Location happens to be a Bank Branch or an ATM, where there is a proper iBeacon or GPS providing additional information about identification, then in such a situation the Authentication can be further simplified based on the type of transaction. In this paper, we discuss in detail location based authentication and how these can be effectively applied in enhancing the mobile banking services.

МЕТАМАТЕМАТИЧЕСКАЯ МОДЕЛЬ МУЛЬТИМОДАЛЬНОЙ ЖЕСТОВОЙ АУТЕНТИФИКАЦИИ ПРИ ПОМОЩИ ДВУХ НЕЗАВИСИМЫХ МОБИЛЬНЫХ УСТРОЙСТВ

МЕТАМАТЕМАТИЧЕСКАЯ МОДЕЛЬ МУЛЬТИМОДАЛЬНОЙ ЖЕСТОВОЙ АУТЕНТИФИКАЦИИ ПРИ ПОМОЩИ ДВУХ НЕЗАВИСИМЫХ МОБИЛЬНЫХ УСТРОЙСТВ

A hybrid encryption/hiding method for secure transmission of biometric data in multimodal authentication system

Biometric security is a fast growing area that gains an increasing interest in the last decades. Digital encryption and hiding techniques provide an efficient solution to protect biometric data from accidental or intentional attacks. In this paper, a highly secure encryption/hiding scheme is proposed to ensure secure transmission of biometric data in multimodal biometric identification/authentication system. The secret fingerprint and iris vectors are sparsely approximated using accelerated iterative hard thresholding technique and then embedded in the host Slantlet-SVD domain of face image. Experiments demonstrate the efficiency of our technique for both encryption and hiding purpose, where the secret biometric information is well encrypted and still extractable with high fidelity even though the carrier image is seriously corrupted. Our experimental results show the efficiency of the proposed technique in term of robustness to attacks, Invisibility, and security.

A Study on Enhancing Mobile Banking Services using Location based Authentication

Every now and then mobile users are increasing in exponentially all over the world, which leads to the growth of mobile-enabled services like mobile banking. The smart phone now available in the market having the ability to do all the functions that people can do olden days using their personal computers. The introduction of mobile communication technology modernization, innovation and globalization are increasingly driving the banking services to become ubiquitous, personalized, convenience, disseminative and secured. Mobile Banking Authentication has evolved over time to include several parameters such as Biometric, Location, Context, History, Profile etc. In this paper, we discuss new mobile banking services like Digital deposit apps, advanced bill payment apps, and Electronic meeting for mini loan services and Mobile payment apps. We can provide higher security for these new services through an intelligent multi-modal Authentication with Location Awareness. Here the location, where the mobile banking transaction has been executed is captured giving the additional option for a Bank to verify if the transaction has been executed normally or if the parameters are at variance with normal practice. If the Location happens to be very in a different country, an additional verification process can be introduced adding to the entropy of Authentication. If the Location happens to be a Bank Branch or an ATM, where there is a proper iBeacon or GPS providing additional information about identification, then in such a situation the Authentication can be further simplified based on the type of transaction. In this paper, we discuss in detail location based authentication and how these can be effectively applied in enhancing the mobile banking services.

Wavelet Based Finger Knuckle and Finger vein Authentication System

Biometrics is the prominent technology for accurate and safe detection of claim identity. This paper proposes a novel multimodal authentication system using finger knuckle (FK) and finger vein (FV). Finger Knuckle has unique bending and makes this a distinctive biometric identifier. The vein pattern of all fingers of human being is not same. Each finger of same person has different vein pattern. It is the hidden part which is not seen by normal eye sight hence less possible to forge. The system consists of proposed prototype finger knuckle and finger vein image capturing devices, formation of own FK and FV image database acquired from proposed devices. Here feature extraction of FK images is based on Walsh Wavelet Transform and FV image on Hybrid Wavelet Transform. Proposed multimodal biometric authentications integrate transformed domain features vector of FK and FV at score level fusion using Bayesian and weighted sum method. The fusion of these two modalities using Bayesian method demonstrated the recognition accuracy of 98.3% and weighted sum 98.5 %. Various weights of finger knuckle and finger vein affects the recognition accuracy. The better recognition accuracy is obtained at weight of 0.8 and 0.2. The performance index is improved i.e 98.5% and the Error equal rate is 1.5% as compare to unimodal biometric. Error equal rate is reduced by 10% than individual biometric system. For N user with M 1 and M 2 as test and training samples, for verification of one user, matching complexity is O (M 1 M 2 ) and for N user O(M 1 M 2 x N). For identification, (N x M 1 ) test samples and (N x M 2 ) training samples are considered. So matching complexity is O [N (N-1) x M 1 ] for each biometric. Using conventional matching the complexity is O [N (N-1) x M 1 M 2 ]. For multimodal biometric using FK and FV, matching complexity is O 2[N (N-1) x M 1 ]. It shows great reduction in matching complexity using the proposed algorithms.

Biometric Authentication Using Fused Multimodal Biometric

Biometrics are basically based on the expansion of pattern recognition systems. At present, electronic or optical sensors like cameras and scanning devices are used to capture images, recordings or measurements of a person's ‘unique’ characteristics. These technologies are being utilized across a range of applications like security, prevention of cyber crime and border control, public aid/social benefits, customs, immigration, passport and healthcare identity verification, as well as commercial enterprises use. Most biometric systems that are typically use a single biometric trait to establish identity have some challenges like Noise in sensed data which increases False Acceptance Rate (FAR) of the system, Non-universality which reduces Genuine Acceptance Rate (GAR). Hence the security afforded by the biometric system mitigates its benefits. In this paper, we propose a Fused Multimodal systems which also have several advantages over unibiometric systems such as, enhanced verification accuracy, larger feature space to accommodate more subjects and higher security against spoofing. The proposed enhanced multimodal authentication system is based on feature extraction(using fingerprint, retina and fingervein) and key generation (using RSA). The experimental evaluation implemented using MATLAB 2014, illustrates the significance improvement in the performance of multimodal biometrics with RSA have GAR of 95.3% and FAR of 0.01%.

Learning Human Identity From Motion Patterns

We present a large-scale study exploring the capability of temporal deep neural networks to interpret natural human kinematics and introduce the first method for active biometric authentication with mobile inertial sensors. At Google, we have created a first-of-its-kind data set of human movements, passively collected by 1500 volunteers using their smartphones daily over several months. We compare several neural architectures for efficient learning of temporal multi-modal data representations, propose an optimized shift-invariant dense convolutional mechanism, and incorporate the discriminatively trained dynamic features in a probabilistic generative framework taking into account temporal characteristics. Our results demonstrate that human kinematics convey important information about user identity and can serve as a valuable component of multi-modal authentication systems. Finally, we demonstrate that the proposed model can also be successfully applied in a visual context.

Continuous and transparent multimodal authentication: reviewing the state of the art

Individuals, businesses and governments undertake an ever-growing range of activities online and via various Internet-enabled digital devices. Unfortunately, these activities, services, information and devices are the targets of cybercrimes. Verifying the user legitimacy to use/access a digital device or service has become of the utmost importance. Authentication is the frontline countermeasure of ensuring only the authorized user is granted access; however, it has historically suffered from a range of issues related to the security and usability of the approaches. They are also still mostly functioning at the point of entry and those performing sort of re-authentication executing it in an intrusive manner. Thus, it is apparent that a more innovative, convenient and secure user authentication solution is vital. This paper reviews the authentication methods along with the current use of authentication technologies, aiming at developing a current state-of-the-art and identifying the open problems to be tackled and available solutions to be adopted. It also investigates whether these authentication technologies have the capability to fill the gap between high security and user satisfaction. This is followed by a literature review of the existing research on continuous and transparent multimodal authentication. It concludes that providing users with adequate protection and convenience requires innovative robust authentication mechanisms to be utilized in a universal level. Ultimately, a potential federated biometric authentication solution is presented; however it needs to be developed and extensively evaluated, thus operating in a transparent, continuous and user-friendly manner.

Multimodal authentication on smartphones: Combining iris and sensor recognition for a double check of user identity

Iris recognition on mobile devices is a challenging task; performing acquisition via the embedded sensors can introduce the sensor interoperability problem. Biometric systems developed so far are limited in their ability of comparing biometric data originated by different sensors because they operate under the assumption that the data to be compared are obtained using the same sensor. This problem led to the development of biometric recognition algorithms able to work independently from the data source. In this paper, we get around the sensor interoperability problem leveraging on the picture differences due to acquisition by different sensors. We present a novel system that combines the recognition of user's iris and user's device, i.e. something the user is plus something the user has. To do so, we adopted an iris recognition algorithm, namely Cumulative SUMs, and a well-known technique in the image forensic field for camera source identification based on the extraction of the Sensor Pattern Noise. The two identification processes are performed on the same picture leading to a system with a good trade-off between ease of use and accuracy. The approach is tested on MICHE, a database composed by iris images captured with different mobile devices in unconstrained acquisition conditions.

Feature Level Fusion the Performance of Multimodal Biometric Systems

paper proposed the use of multimodal feature-level fusion to prove the improvement performance of multimodal authentication. Different algorithm used for features extraction, LG for extracting FKP features, LPQ for iris and Palmprint features extraction, and PCA for extracting face features. Results brought to light that the multimodal authentication process gained higher performance than single modality. The biometric performance using feature-level fusions under Z-score, Tanh, Median, and Min-Max normalization has been demonstrated in this paper.

Multi-modal fusion of palm-dorsa vein pattern for accurate personal authentication

This paper proposes an efficient multi-modal authentication system which makes use of palm-dorsa vein pattern. There are four levels of fusion in the system and they are multi-algorithm fusion, data fusion, feature fusion and score fusion. Multi-algorithm fusion is applied to extract genuine vein patterns from a vein image by using various vein extraction algorithms. All false vein patterns are eliminated from the extracted patterns through data fusion. Three types of features are obtained from each extracted vein pattern and they are shape features, minutiae and features obtained from hand boundary shape. Third level of fusion is at feature level to fuse minutiae and shape features. Finally, fused features and hand boundary shape features are matched to obtain matching scores which are fused at score level. The proposed system has been tested on the database acquired from 4120 images of 1030 subjects. It has achieved an accuracy of 100%. Experimental results reveal that it performs better than other existing systems.

Feature Selection in Multimodal Authentication Using Lu Factorization with Cseam Model

Multimodal authentication is one of the prime concepts in current applications of real scenario. Various approaches have been proposed in this aspect. In this paper, an intuitive strategy is proposed as a framework for providing more secure key in biometric security aspect. Initially the features will be extracted through PCA by SVD from the chosen biometric patterns, then using LU factorization technique key components will be extracted, then selected with different key sizes and then combined the selected key components using convolution kernel method (Exponential Kronecker Product - eKP) as Context-Sensitive Exponent Associative Memory model (CSEAM). In the similar way, the verification process will be done and then verified with the measure MSE. This model would give better outcome when compared with SVD factorization[1] as feature selection. The process will be computed for different key sizes and the results will be presented.

Pattern Recognition Using Context Dependent Memory Model (CDMM) in Multimodal Authentication System

Pattern recognition is one of the prime concepts in current technologies in both private and public sectors. The analysis and recognition of two or more patterns is a complex task due to several factors. The consideration of two or more patterns requires huge space for keeping the storage media as well as computational aspect. Vector logic gives very good strategy for recognition of patterns. This paper proposes pattern recognition in multimodal authentication system with the use of vector logic and makes the computation model hard and less error rate. Using PCA two to three biometric patterns will be fusion and then various key sizes will be extracted using LU factorization approach. The selected keys will be combined using vector logic, which introduces a memory model often called Context Dependent Memory Model (CDMM) as computational model in multimodal authentication system that gives very accurate and very effective outcome for authentication as well as verification. In the verification step, Mean Square Error (MSE) and Normalized Correlation (NC) as metrics to minimize the error rate for the proposed model and the performance analysis will be presented.

A Multimodal User Authentication System Using Faces and Gestures.

As a novel approach to perform user authentication, we propose a multimodal biometric system that uses faces and gestures obtained from a single vision sensor. Unlike typical multimodal biometric systems using physical information, the proposed system utilizes gesture video signals combined with facial images. Whereas physical information such as face, fingerprints, and iris is fixed and not changeable, behavioral information such as gestures and signatures can be freely changed by the user, similar to a password. Therefore, it can be a countermeasure when the physical information is exposed. We aim to investigate the potential possibility of using gestures as a signal for biometric system and the robustness of the proposed multimodal user authentication system. Through computational experiments on a public database, we confirm that gesture information can help to improve the authentication performance.

Designing an accurate hand biometric based authentication system fusing finger knuckleprint and palmprint

This paper proposes an accurate and efficient multi-modal authentication system that makes use of palm and knuckleprint samples. Biometric images are transformed using the proposed sign of local gradient (SLG). Corner features are extracted from vcode and hcode and are tracked using geometrically and statistically constrained Lucas and Kanade tracking algorithm. The proposed highly uncorrelated features (HUF) measure is used to match two query images. The proposed system is tested on publicly available PolyU and CASIA palmprint databases along with PolyU Knuckleprint database. Several sets of chimeric bi-modal as well as multimodal databases are created in order to test the proposed system. Experimental results reveal that the proposed multi-modal system achieves CRR of 100% with an EER as low as 0.01% over all created chimeric multimodal datasets.