Real-time Authentication System Research Articles

Deep Learning Strategies for Netbanking Fraud Detection using Face Biometrics

The goal of Internet banking is to develop a secure authentication system for the banking sector. Security providers for online banking must be responsive to security requirements. While there is no doubt that banking transactions should be protected from threats or security attacks on multiple levels, service providers should incorporate security into their service offerings. And you have probably heard a lot about hacker methods for stealing any logical password or pin number, identity theft, credit card fraud, or other security breaches. Identification, which can be equated to a username in the existing framework, is used to authorise and grant access to a system. Because usernames are easily forgotten, they are used to verify that the intended user is who he or she claims to be - the authentication process. Biometric authentication and identity systems are the most recent solutions to security and privacy concerns. Face Recognition is the study of physical or behavioural characteristics of humans that are used to identify people and verify whether they are authorised or not. These physical characteristics of a person include fingerprints, face, hand geometry, voice, palm -vein, and iris biometric device. Create a real-time authentication system for online banking that uses face biometrics for approved users. The project's goal is to create a fully functional face recognition and verification system, as well as to understand the key features of these important technologies, specifically those relating to the technological, application domain, social environmental system, and performance factors. And provide a joint account access system to allow multiple people to access the same accounts by giving original account holders access control. The blockchain is created when a transaction is stored in a database. When a secondary user logs into the account, the access information is sent directly to the primary account holder. This blockchain technology will secure the authentication system of the net banking application.

A novel two-dimensional ECG feature extraction and classification algorithm based on convolution neural network for human authentication

Abstract A biometrics-based authentication system is usually a better security solution than traditional systems which are heavily reliant on passwords, personal identification numbers or smart cards. Electrocardiogram (ECG) is one of the most promising approaches for biometrics-based authentication in recent years, because, unlike other biometrics, it assures aliveness of the person being authenticated. In this paper, we present a novel authentication system using an efficient feature detection algorithm and a convolutional neural network (CNN) based on ECG for human authentication. Our system processes ECG signals through two main phases: a feature detection phase and an authentication phase. In the feature detection phase, preprocessing was performed first to remove as much noise as possible and straighten the ECG signals. Then, the proposed scanning and removing methods are used to extract the main features from the signals that have negative peaks, high-grade noise and baseline drifts with higher accuracy than existing algorithms. In the authentication phase, we proposed a 12-layer CNN to authenticate the ECG signals. We also introduced a new database (MWM-HIT database), which is suitable for training and validating authentication systems. In addition, we used all records from the PTB, CYBHi, and MIT-BIH arrhythmia databases for comparison between the proposed system and other systems. We achieved an average accuracy, sensitivity and positive predictivity of 97.92%, 96.96% and 98.79%, respectively for detecting all peaks on all records from the collected database and an accuracy of 99.96%, sensitivity of 99.99% and positive predictivity of 99.98% for detecting all peaks on the MIT-BIH database for ten seconds of lead II ECG signals. The proposed model is able to authenticate the ECG signals with an equal error rate (EER) of 1.63%, 4.47%, and 4.86% when using lead II from PTB, CYBHi and the collected databases, respectively. The proposed system is highly usable in a real-time authentication system.

뇌파 기반의 인증시스템을 위한 EEG 암호화 기법

Gradually increasing the value of the technology, the techniques of the various security systems to protect the core technology have been developed. The proposed security scheme, which uses both a Password and the various devices, is always open by malicious user. In order to solve that problem, the biometric authentication systems are introduced but they have a problem which is the secondary damage to the user. So, the authentication methods using EEG(Electroencephalography) signals were developed. However, the size of EEG signals is big and it cause a lot of problems for the real-time authentication. And the encryption method is necessary. In this paper, we proposed an efficient real-time authentication system applied encryption scheme with junk data using chaos map on the EEG signals.

PERSONAL AUTHENTICATION USING PALMPRINT WITH SOBEL CODE, CANNY EDGE AND PHASE CONGRUENCY FEATURE EXTRACTION METHOD

Palmprint recognition refers to recognizing a person on the basis of palmprint features. In this paper, we have proposed a palmprint based biometric authentication method with improvement in accuracy, so as to make it a real time palmprint authentication system. Several edge detection methods, Directional operator, Wavelet transform, Fourier transform etc. are available to extract line feature from the palmprint. In this paper, Sobel Code operators, Canny edge and Phase Congruency methods are applied to the palmprint image to extract palmprint features. The extracted Palmprint features are stored in Palmprint feature vector. The corresponding feature vectors are matched using sliding window with Hamming Distance similarity measurement method. In this paper, a Min Max Threshold Range (MMTR) method is proposed that helps in increasing overall system accuracy by reducing the False Acceptance Rate (FAR). The person authenticated by reference threshold is again verified by second level of authentication using MMTR method. Experimental results indicate that the MMTR method improves the False Acceptance Rate drastically. The accuracy improvement leads to proposed real time authentication system.

FAST PALMPRINT AUTHENTICATION BY SOBEL CODE METHOD

The ideal real time personal authentication system should be fast and accurate to automatically identify a person’s identity. In this paper, we have proposed a palmprint based biometric authentication method with improvement in time and accuracy, so as to make it a real time palmprint authentication system. Several edge detection methods, wavelet transform, phase congruency etc. are available to extract line feature from the palmprint. In this paper, Multi-scale Sobel Code operators of different orientations (0, 45, 90, and 135) are applied to the palmprint to extract Sobel-Palmprint features in different directions. The Sobel-Palmprint features extracted are stored in SobelPalmprint feature vector and matched using sliding window with Hamming Distance similarity measurement method. The sliding window method is accurate but time taking process. In this paper, we have improved the sliding window method so that the matching time reduces. It is observed that there is 39.36% improvement in matching time. In addition, a Min Max Threshold Range (MMTR) method is proposed that helps in increasing overall system accuracy by reducing the False Acceptance Rate (FAR). Experimental results indicate that the MMTR method improves the False Acceptance Rate drastically and improvement in sliding window method reduces the comparison time. The accuracy improvement and matching time improvement leads to proposed real time authentication system.

J1602-2-5 ウェブカメラを用いた簡便認証システムの構築(機械の知能化:異分野からのアプローチ(2))

This research aims at constructing a real-time authentication system from human faces in which the user action is probably not needed, and the cheap web-camera is used. The number of parameters needed in this system is six, including shape and position of eyes, nose and mouth. It is difficult to obtain a set of uniform data of nose and mouth for a group because of the great influence of the individual difference, we. specify their areas from the coordinate of the eyes, mosaic the area and adopt the standard deviation from the distribution of the color as the data for authentication. The self-organization map is used for the certification. The speed can be expected in the certification, though time is needed for the map preparation in the registration stage. The system is tested by recognizing six registered persons 10 times and the success rate of 83% is obtained.