Personal Authentication Research Articles

Optimized Multi-Model Biometric Based Human Authentication using Deep Neural Network

Biometrics provides greater security and usability than conventional personal authentication methods. Fingerprints, facial identification systems and voice recognition systems are the features that biometric systems can use. To improve biometric authentication, the proposed method considered that the input image is iris and fingerprint; at first, pre-processing is performed through histogram equalization for all image inputs to enhance the image quality. Then the extraction process of the feature will be performed. The suggested method uses modified Local Binary Pattern (MLBP), GLCM with orientation transformation, and DWT features next to the extracted features to be combined for feature extraction. Then the optimum function is found with the Rider Optimization Algorithm (ROA) for all MLBP, GLCM and DWT. Eventually, the approach suggested is accepted. Deep Neural Network (DNN) performs the proposed authentication process. A DNN is a multilayered artificial neural network between the layers of input and output. The DNN finds the right mathematical manipulation to turn the input into the output, whether it is an acknowledged image or not. Suggested process quality is measured in terms of reliability recognition. In the MATLAB platform, the suggested approach is implemented.

A unified approach for skin colour segmentation using generic bivariate Pearson mixture model

Skin colour segmentation is rapidly growing area of research in computer science for identification and authentication of persons. In this paper, a novel generic bivariate Pearsonian mixture model for skin colour segmentation is proposed. It is observed that the hue and saturation of the colour image better characterise the features of the individual human races. In general, the human race can be characterised in to three categories namely Asian, African and European. The feature of the skin colour of these races are modelled by three different bivariate Pearsonian distributions. The combination of all these three races of people in an image can be characterised by a three component mixture model. Deriving the updated equations of the EM-algorithm, the generic bivariate Pearson mixture model parameters are estimated. The initialisation of the model parameters are done through moment method of estimation and K-means algorithm. The segmentation algorithm is developed using component maximum likelihood under Bayesian frame. The performance of the proposed algorithm is carried by experimentation with random sample of five images and computing the segmentation performance metrics such as PRI, GCE and VOI. The efficiency of the proposed model with that of bivariate GMM is carried through confusion matrix and ROC curves. It is observed that the proposed algorithm outperforms the existing algorithms.

Multimodal biometrics with serial, parallel and hierarchical mode at decision level fusion

<p>Biometric based personal authentication is playing a vital role in various security based applications. This paper presents the effective fusion of fingerprint, palmprint and iris traits at decision level. Combining different traits at the decision level is a challenging task due to less information available at this level. The focus of the work is to examine the performance of multimodal biometrics at decision level fusion in three different i.e. serial, parallel and hierarchical modes of operation. Serial mode is performed by taking unimodals serially while parallel mode of operation is carried out by processing all modals simulatenously using Majority Voting Rule and the hierarchical mode of operation is performed with proper combination of traits in parallel and serial mode using AND and OR rule. The experiments are performed on 100 different users from publically available FVC2006 fingerprint database, CASIA V1 palmprint database and IITD iris database. The experimental results suggest that proper fusion of different traits in hierarchical way can give best performance even at decision level fusion as compared to serial and parallel mode of operation.</p>

Continuous Authentication of Automotive Vehicles Using Inertial Measurement Units.

The concept of Continuous Authentication is to authenticate an entity on the basis of a digital output generated in a continuous way by the entity itself. This concept has recently been applied in the literature for the continuous authentication of persons on the basis of intrinsic features extracted from the analysis of the digital output generated by wearable sensors worn by the subjects during their daily routine. This paper investigates the application of this concept to the continuous authentication of automotive vehicles, which is a novel concept in the literature and which could be used where conventional solutions based on cryptographic means could not be used. In this case, the Continuous Authentication concept is implemented using the digital output from Inertial Measurement Units (IMUs) mounted on the vehicle, while it is driving on a specific road path. Different analytical approaches based on the extraction of statistical features from the time domain representation or the use of frequency domain coefficients are compared and the results are presented for various conditions and road segments. The results show that it is possible to authenticate vehicles from the Inertial Measurement Unit (IMU) recordings with great accuracy for different road segments.

A Survey of Behavioral Biometric Gait Recognition: Current Success and Future Perspectives

In today digital society, vulnerability to person authentication is a serious issue in real time scenarios like (airport, hospital, metro stations, etc.). This issue has increased the growth of video surveillance security systems. In recent decades behavioral biometric trait gait has emerged as a potential surveillance monitoring system because of its inconspicuous and unperceivable nature. Even more human gait has a benefit that it can be tracked at a distance and under low resolution videos. Finally, it is difficult to impersonate gait features. In this article, we comprehensively investigate the past and current research development in vision-based (VB) gait recognition. We give a brief description of feature selection and classification techniques used in gait recognition. The article extensively investigates feature representation techniques, classified into model-based and model-free. The article also provides a detail description of databases that are available for research purposes classified into two categories: VB and sensor-based. We extensively examine factors that affect gait recognition, and current research was done to cope with these factors. Moreover, this article proposes future perspectives after investigating state-of-art literature that can be more helpful to experts and new comers in gait recognition. In last, we also give a brief description of the proposed workflow.

ECG based person authentication using empirical mode decomposition and discriminant analysis

Person identification or authentication through biometric features has been widely applied for basic access and high-level security. But conventional biometrics such as fingerprints and irises tend to be easily faked or duplicated. Therefore a new biometric modality is needed to overcome that problem. In this paper, we simulate a new model of biometric systems using physical signals of the body. The proposed biometric system is based on ECG signals as a characteristic of each subject. A total of 110 raw ECG signals with a duration of 5 seconds from 11 participants were demonstrated in the proposed system. Empirical mode decomposition (EMD) and statistical analysis are used for feature extraction. Discriminant analysis with cross-validation was applied to test the performance of the proposed method. In this research, the highest accuracy of 93.6% was obtained using subspace discriminant in the scenario of all feature attributes as predictors.

ECG Based Biometric using Wavelet Packet Decomposition

Biometric technology has been commonly used for authentication. Fingerprint or iris become one of the biometrics that is widely applied. However, this type of biometrics tends to be easily falsified and damaged. So it is misused for manipulating actions and even crime. Therefore a new biometric method is needed to overcome this problem. One potential modality is biometrics based on an electrocardiogram (ECG) signal. This research simulates a one-lead ECG waveform for person authentication. ECG waves were taken from eleven healthy adult volunteers with a length of 60 seconds. ECG waves from each person are segmented into 10 sections so that a total of 110 ECG waves are used for person authentication simulations. All noise of the ECG waves was removed using a bandpass filter to reduce artifacts and high-frequency noise. Wavelet packet decomposition (3 Level) was applied to decompose the signal in several intrinsic parts so that typical wave information can be retrieved. Entropy-based feature extraction applied to all decomposed signals. A total of 14 entropy features have been calculated and used as predictors in the classification process. Validation and performance tests are carried out by cross-validation combined with linear discriminant analysis and support vector machines with five scenarios. The proposed method provides the highest accuracy of 71.8% using discriminant analysis and cubic support vector machine. The best accuracy value was achieved if all entropy features from all wavelet decomposition levels are used as predictors in the classification process. This research is expected to be a reference that ECG has the potential to become a future biometric modality.

Fusion of Neuro-Signals and Dynamic Signatures for Person Authentication.

Many biometric systems based on physiological traits such as ones facial characteristics, iris, and fingerprint have been developed for authentication purposes. Such security systems, however, commonly suffer from impersonation attacks such as obfuscation, abrasion, latent samples, and covert attack. More conventional behavioral methods, such as passwords and signatures, suffer from similar issues and can easily be spoofed. With growing levels of private data readily available across the internet, a more robust authentication system is needed for use in emerging technologies and mobile applications. In this paper, we present a novel multimodal biometric user authentication framework by combining the behavioral dynamic signature with the the physiological electroencephalograph (EEG) to restrict unauthorized access. EEG signals of 33 genuine users were collected while signing on their mobile phones. The recorded sequences were modeled using a bidirectional long short-term memory neural network (BLSTM-NN) based sequential classifier to accomplish person identification and verification. An accuracy of 98.78% was obtained for identification using decision fusion of dynamic signatures and EEG signals. The robustness of the framework was also tested against 1650 impersonation attempts made by 25 forged users by imitating the dynamic signatures of genuine users. Verification performance was measured using detection error tradeoff (DET) curves and half total error rate (HTER) security matrices using true positive rate (TPR) and false acceptance rate (FAR), resulting in 3.75% FAR and 1.87% HTER with 100% TPR for forgery attempts.

A GEO - Tagging Based Hybrid Mobile Attendance System

Biometrics technologies verify identity through characteristics such as fingerprints, faces, irises, retinal patterns, palm prints, voice, hand-written signatures, and so on. These techniques, which use physical data, are receiving attention as a personal authentication method that is more convenient than conventional methods such as password or ID cards because it uses data taken from measurements and such data is unique to the individual and remains so throughout one’s lifetime. Geo-tagging is the process of adding geographical information to various media in the form of metadata. The data usually consists of coordinates like latitude and longitude, but may even include bearing, altitude, distance and place names. By combining the above services, we can help the public and private sector offices like Survey Department, Revenue Department, Electricity department, Telephone Department, Public Works Department (PWD), Transport Department (NH, KSRTC etc.) to take care of the employee’s attendance by asking them to install this proposed application in their smart phone.

Bagged ensemble of fuzzy classifiers and feature selection for handwritten signature verification

Handwritten signature verification is an important research area in the field of person authentication and biometric identification. There are two known methods for handwriting signature verification: if it is possible to digitize the speed of pen movement, then verification is said to be on-line or dynamic; otherwise, when only an image of handwriting is available, verification is said to be off-line or static. It is proved that when using dynamic verification, a greater accuracy is achieved than when using static verification. In the present work, the amplitudes, frequencies, and phases of the harmonics extracted from the signature signals of the X and Y coordinates of the pen movement using a discrete Fourier transform are used as characteristics of the signature. All signals are pre-processed in advance, including the elimination of gaps, the elimination of the angle of inclination, the normalization of position and scaling. A fuzzy classifier is proposed as a signature verification tool based on the features obtained. The work examines the effectiveness of this tool in the ensemble, as well as using a procedure for feature selection. To build an ensemble of classifiers, a well-known bagging method is used, and the feature selection is based on the determination of mutual information between a feature and a class of an object. Experiments on signature verification on the SVC2004 data set with the construction of a fuzzy classifier and ensembles of three, five, seven and nine fuzzy classifiers were conducted. Experiments were carried out both with the use of the feature selection procedure and without selection. The efficiency of the classifiers constructed is compared with each other and with known analogues: decision trees, support vector machines, discriminant analysis and k-nearest neighbors.

Effective segmentation of sclera, iris and pupil in noisy eye images

In today’s sensitive environment, for personal authentication, iris recognition is the most attentive technique among the various biometric technologies. One of the key steps in the iris recognition system is the accurate iris segmentation from its surrounding noises including pupil and sclera of a captured eye-image. In our proposed method, initially input image is preprocessed by using bilateral filtering. After the preprocessing of images contour based features such as, brightness, color and texture features are extracted. Then entropy is measured based on the extracted contour based features to effectively distinguishing the data in the images. Finally, the convolution neural network (CNN) is used for the effective sclera, iris and pupil parts segmentations based on the entropy measure. The proposed results are analyzed to demonstrate the better performance of the proposed segmentation method than the existing methods.

Biometric person authentication framework using polynomial curve fitting-based ECG feature extractio

The applications of modern biometric techniques for person identification systems rapidly increase for meeting the rising security demands. The distinctive physiological characteristics are more correctly measurable and trustworthy since previous measurements are not appropriately made for physiological properties. While a variety of strategies have been enabled for identification, the electrocardiogram (ECG)-based approaches are popular and reliable techniques in the senses of measurability, singularity, and universal awareness of heartbeat signals. This paper presents a new ECG-based feature extraction method for person identification using a huge amount of ECG recordings. First of all, 1800 heartbeats for each of the 36 subjects have been obtained from the widespread and large MIT-BIH database (MITDB) downloaded from the PhysioBank archive. Then the fiducial points of each heartbeat were determined and fourteen different features were extracted utilizing these fiducial points. Next, the polynomial curve fitting-based dimension reduction technique was employed on the extracted fourteen features. Furthermore, six celebrated classifiers including artificial neural networks (ANNs), decision trees (DTs), Fisher linear discriminant analysis (FLDA), K-nearest neighbors (K-NNs), naive Bayes (NB), and support vector machines (SVMs) were applied for the verification and performance evaluation of the proposed study. Also, as a different classifier, temporal classification and random forest was utilized for a benchmark classification. The highest performance was attained with 95.46\% accuracy rate in the case of the SVM classifier. The experimental results emphasize that the proposed ECG-based feature extraction method gives insightful merit for biometric-based person authentication systems.

Biometric-Based Attendance Tracking System for Education Sectors: A Literature Survey on Hardware Requirements

The application of biometric recognition in personal authentication enables the growth of this technology to be employed in various domains. The implementation of biometric recognition systems can be based on physical or behavioral characteristics, such as the iris, voice, fingerprint, and face. Currently, the attendance tracking system based on biometric recognition for education sectors is still underutilized, thus providing a good opportunity to carry out interesting research in this area. As evidenced in a typical classroom, educators tend to take the attendance of their students by using conventional methods such as by calling out names or signing off an attendance sheet. Yet, these types of methods are proved to be time consuming and tedious, and sometimes, fraud occurs. As a result, significant progress had been made to mark attendance automatically by making use of biometric recognition. This progress enables a new and more advanced biometric-based attendance system being developed over the past ten years. The setting-up of biometric-based attendance systems requires both software and hardware components. Since the software and hardware sections are too broad to be discussed in one paper, this literature survey only provides an overview of the types of hardware used. Emphasis is then placed on the microcontroller platform, biometric sensor, communication channel, database storage, and other components in order to assist future researchers in designing the hardware part of biometric-based attendance systems.

An Agent Based Multimodal Biometric Method for Secure Systems

A security system based on biometrics of a person depends on the features of a person. These can be physical features or behavioral features. User authentication is necessary for security control system and intelligent human computer interface, so that only the real user accesses it. We present a method for the authentication of person with help of multimodal data which includes face and speech. Agent based system has been used for fusion of these data which gives us a more reliable, efficient and secure biometric system. A method for face detection for recognition of faces has been given. For speech recognition Artificial Neural Network has been used. Both these combined together identify the speaker. This multimodal biometric method will give highly reliable secure system.

An Exhaustive Multi Factor Face Authentication Using Neuro-Fuzzy Approach

The face authentication is a challenging task to validate the user with uncontrolled environment like variations on expression, pose, illumination and occlusion. In order to address these issues, the proposed work provides solution by considering all these factors in inter and intra personal face authentication. During enrollment process, the facial region of still image for the authorized user is detected and features are extracted using local tetra pattern (LTrP) technique. The features are given as input to the neural network namely fuzzy adaptive learning control network (FALCON) for training and classification of features. During authentication process, an image that can vary with expression, pose, illumination and occlusion factors is taken as test image and the test image is applied with LTrP and FALCON to train the features of test image. Then, these trained features are compared with existing feature set by using new proposed multi factor face authentication algorithm to authenticate a person. This work is evaluated among 1150 face images which are collected from JAFFE, Yale, ORL and AR datasets. The overall performance of the work is evaluated by authenticating 1106 images from 1150 constrained images. The second phase of the research work finally produces highest recognition rate of 96% among conventional methods.

Phacoemulsification Cataract Surgery Affects the Discriminative Capacity of Iris Pattern Recognition

Cataract is a common ophthalmic disorder and the leading cause of blindness worldwide. While cataract is cured via surgical procedures, its impact on iris based biometric recognition has not been effectively studied. The key objective of this research is to assess the effect of cataract surgery on the iris texture pattern as a means of personal authentication. We prepare and release the IIITD Cataract Surgery Database (CaSD) captured from 132 cataract patients using three commercial iris sensors. A non-comparative non-randomized cohort study is performed on the iris texture patterns in CaSD and authentication performance is studied using three biometric recognition systems. Performance is lower when matching pre-operative images to post-operative images (74.69 ± 9.77%) as compared to matching pre-operative images to pre-operative images (93.42 ± 1.76%). 100% recognition performance is observed on a control-group of healthy irises from 68 subjects. Authentication performance improves if cataract affected subjects are re-enrolled in the system, though re-enrollment does not ensure performance at par with pre-operative scenarios (86.67 ± 5.64%). The results indicate that cataract surgery affects the discriminative nature of the iris texture pattern. This finding raises concerns about the reliability of iris-based biometric recognition systems in the context of subjects undergoing cataract surgery.

Signify: Signature Verification Technique using Convolutional Neural Network

Signature is one of the biometric traits that are being used in person authentication and due to its dominant usage; it became one of the top subjects of forgery. In this study, a signature verification using Convolutional Neural Network (CNN) is proposed. With the use of transfer learning, inception-v3 is mainly used for the feature extraction of data samples and for classification of signatures. The proposed method is assessed on dataset of handwritten signatures gathered from 4 people with 100 signatures each. The testing results determine the threshold value which is 96.43%. Factors that affect the accuracy of the result were also identified.

Deep Neural Network-Based Gait Classification Using Wearable Inertial Sensor Data.

Human gait has been regarded as a useful behavioral biometric trait for personal identification and authentication. This study aimed to propose an effective approach for classifying gait, measured using wearable inertial sensors, based on neural networks. The 3-axis accelerometer and 3-axis gyroscope data were acquired at the posterior pelvis, both thighs, both shanks, and both feet while 29 semi-professional athletes, 19 participants with normal foot, and 21 patients with foot deformities walked on the 20-meter straight path. The classifier based on the gait parameters and fully connected neural network was developed by applying 4-fold cross-validation to 80% of the total samples. For the test set that consisted of the remaining 20% of the total samples, this classifier showed an accuracy of 93.02% in categorizing the athlete, normal foot, and deformed foot groups. Using the same model validation and evaluation method, up to 98.19% accuracy was achieved from the convolutional neural network-based classifier. This classifier was trained with the gait spectrograms obtained from the time-frequency domain analysis of the raw acceleration and angular velocity data. The classification based only on the pelvic spectrograms exhibited an accuracy of 94.25% even without requiring a time-consuming and resource-intensive process for feature engineering. The notable performance and practicality in gait classification achieved by this study suggest potential applicability of the proposed approaches in the field of biometrics.

Personal Authentication Mechanism Based on Finger Knuckle Print

For authentication purposes, the identification and verification of a user is done by biometric traits like finger print, face, iris and gait, etc. Among the various traits finger print is mostly used in commercial applications for recognizing user's identity. The other hand based modalities such as vein, and finger knuckle are gaining importance. This paper proposes a methodology for secure biometrics authentication using Finger Knuckle Print (FKP). The texture patterns from finger knuckle are extracted using Gabor with Exception-Maximization (EM) algorithm and the feature vectors from these texture patterns are acquired using Scale Invariant Feature Transform (SIFT) algorithm. The main focus is to reduce the false rejection rate without increasing the false acceptance rate and to improve the performance over the conventional hand based modalities. The performance is compared with Genuine Acceptance Rate (GAR) and False Rejection Rate (FRR). One of the advantages of FKP authentication is its user friendliness in data collection.

Biometric Authentication through Unification of Finger Dorsal Biometric Traits

This paper presents a novel method for personal authentication of individuals using a deep learning approach. The reported method implements the fusion of two biometric attributes, namely fingernail plates and finger knuckles. Both these biometric traits have been extracted from the index, middle and ring fingers of a database of 890 (5 each from 178 persons) low-resolution hand dorsal images. AlexNet, a pre-trained deep learning model, has been tailored for feature extraction to suit the number of classes in the database. Deep learning features are extracted from both the traits using the customized Convolutional Neural Network (CNN). These features have been fused at the score-level and the rank-level for different combinations. Both these levels of fusion have been executed through well-established rules. Score-level fusion results show that verification can be done quite accurately with this multimodal framework. Results also depict that information fusion of these traits at the rank-level can be optimized to give Rank-1 identification rate of a perfect 100%.