Enhancing The Performance Of Neural Network Classifiers Using Selected Biometric Features (original) (raw)

Biometric Identification Using Artificial Neural Network

Artificial Neural Networks (ANN) are the efficient means of prediction and recognition. The ability of the ANN to learn given patterns makes them suitable for such applications. Fingerprint, Face and Retina Recognition are the areas that can be used as a means of biometric verification where the ANN can play a critical rule. But faces of two twins can be of same look, so Fingerprint & Retina (F&R) are unique biometric pattern that can be used as a part of a verification system. An ANN can be configured and trained to handle such variations observed in the texture of the fingerprint & Retina. The specialty of the work is associated with the fact that if the ANN is configured properly it can tackle the variations in the fingerprint& retinal images and that way provides the insights for developing a system which requires the samples for verification and authorization. A system designed to provide authentication decision using the input can be a reliable means of verification. Such a system designed using ANN and using retina input is described here. Experimental results show that the system is reliable enough for considering it as a part of a verification mechanism.

Authentication of individuals using hand geometry biometrics: A neural network approach

Neural Processing …, 2007

Biometric based systems for individual authentication are increasingly becoming indispensable for protecting life and property. They provide ways for uniquely and reliably authenticating people, and are difficult to counterfeit. Biometric based authenticity systems are currently used in governmental, commercial and public sectors. However, these systems can be expensive to put in place and often impose physical constraint to the users. This paper introduces an inexpensive, powerful and easy to use hand geometry based biometric person authentication system using neural networks. The proposed approach followed to construct this system consists of an acquisition device, a pre-processing stage, and a neural network based classifier. One of the novelties of this work comprises on the introduction of hand geometry's related, position independent, feature extraction and identification which can be useful in problems related to image processing and pattern recognition. Another novelty of this research comprises on the use of error correction codes to enhance the level of performance of the neural network model. A dataset made of scanned images of the right hand of fifty different people was created for this study. Identification rates and Detection Cost Function (DCF) values obtained with the system were evaluated. Several strategies for coding the outputs of the neural networks were studied. Experimental results show that, when using Error Correction Output Codes (ECOC), up to 100% identification rates and 0% DCF can M. Faundez-Zanuy 123 202 M. Faundez-Zanuy et al.

Analysis of Training Functions in a Biometric System

One of the commonly used Biometric methods is Face Classification. Face images are obtained from FEI face database. In this paper, different Training Functions of Neural Network are studied. In this research, a face recognition system is suggested based on feedforward backpropagation neural network Neural Network (FFBPNN) model. Each model is constructed separately with one input layer, 3 hidden layers and one output layer). Four ANN training algorithms (TRAINLM, TRAINBFG, TRAINGDX, and TRAINRP) are used to train each model separately. Performances using each of the training algorithms were evaluated based on mean square error and the best training algorithm is found for the face recognition.

Biometric Identification by Means of Hand Geometry and a Neural Net Classifier

This Paper describes a hand geometry biometric identification system. We have acquired a database of 22 people using a conventional document scanner. The experimental section consists of a study about the discrimination capability of different extracted features, and the identification rate using different classifiers based on neural networks.

Review of Biometric system performance, metrics and representation..

Numerous applications for personal identification exist and more are emerging daily. Examples of personal identification applications include immigration and border control, physical access control, time and attendance, computer security, and law enforcement. As a result, the area of biometrics will continue to be an area of interest for many researchers. In the past, the identity of an individual was determined based upon a possession or knowledge of a piece of information. These identification methods can be circumvented by unauthorized sharing or misplacement. However, biometric identifiers cannot be shared easily or forgotten because they are based on potentially distinctive physiological characteristics. This property makes biometrics a viable and perhaps superior approach to personal identification.

Biometric Information Recognition Using Artificial Intelligence Algorithms: A Performance Comparison

IEEE Access, 2022

Addressing crime detection, cyber security and multi-modal gaze estimation in biometric information recognition is challenging. Thus, trained artificial intelligence (AI) algorithms such as Support vector machine (SVM) and adaptive neuro-fuzzy inference system (ANFIS) have been proposed to recognize distinct and discriminant features of biometric information (intrinsic hand features and demographic cues) with good classification accuracy. Unfortunately, due to nonlinearity in distinct and discriminant features of biometric information, accuracy of SVM and ANFIS is reduced. As a result, optimized AI algorithms ((ANFIS) with subtractive clustering (ANFIS-SC) and SVM with error correction output code (SVM-ECOC)) have shown to be effective for biometric information recognition. In this paper, we compare the performance of the ANFIS-SC and SVM-ECOC algorithms in their effectiveness at learning essential characteristics of intrinsic hand features and demographic cues based on Pearson correlation coefficient (PCC) feature selection. Furthermore, the accuracy of these algorithms are presented, and their recognition performances are evaluated by root mean squared error (RMSE), mean absolute percentage error (MAPE), scatter index (SI), mean absolute deviation (MAD), coefficient of determination (R 2), Akaike's Information Criterion (AICc) and Nash-Sutcliffe model efficiency index (NSE). Evaluation results show that both SVM-ECOC and ANFIS-SC algorithms are suitable for accurately recognizing soft biometric information on basis of intrinsic hand measurements and demographic cues. Moreover, comparison results demonstrated that ANFIS-SC algorithms can provide better recognition accuracy, with RMSE, AICc, MAPE, R 2 and NSE values of ≤ 3.85, 2.39E+02, 0.18%, ≥ 0.99 and ≥ 99, respectively.

Neural Network Based Biometric Personal Identification

2007 Frontiers in the Convergence of Bioscience and Information Technologies, 2007

This paper presents biometric personal identification based on iris recognition using neural networks. Personal identification system consists of localization of the iris region and generation of data set of iris images and then iris pattern recognition. In this paper, fast algorithm is proposed for the localization of the inner and outer boundaries of the iris region. Located iris is extracted from an eye image, and, after normalization and enhancement it is represented by a data set. Using this data set a neural network is applied for the classification of iris patterns. Results of simulations illustrate the effectiveness of the neural system in personal identification.

Computational Intelligence for Biometric Applications: a Survey

International Journal of Computing

Biometric systems consist of devices, procedures, and algorithms used to recognize people based on their physiological or behavioral features, known as biometric traits. Computational intelligence (CI) approaches are widely adopted in establishing identity based on biometrics and also to overcome non-idealities typically present in the samples. Typical areas include sample enhancement, feature extraction, classification, indexing, fusion, normalization, and anti-spoofing. In this context, computational intelligence plays an important role in performing of complex non-linear computations by creating models from the training data. These approaches are based on supervised as well as unsupervised training techniques. This work presents computational intelligence techniques applied to biometrics, from both a theoretical and an application point of view.

Biometric Recognition Techniques: A Review

International Journal of Advanced Research in Electrical, Electronics and Instrumentation Energy, 2012

In today‟s world automation is encompassing virtually every walk of life and human control functions are delegated to technical equipment. No doubt this results in emerging requirement of highly reliable personal identification system for authenticated access of resources and to reject imposters. Traditional password based verification systems can be easily hacked when a password is divulged to an unauthorized user. A number of biometric techniques have been proposed for personal identification by various researchers. Biometric includes something which one does not need to remember or carry a token. Biometric based personal authentication systems use physiological or behavioral traits of a person for recognition purpose. Physiological traits include fingerprint, face, hand geometry etc. and behavioral traits are speech, handwriting, key strokes etc. During past few years, there has been remarkable growth in biometric recognition technology due to the increasing requirement of highly...

Classification and Performance of Biometric Authentication

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2021

Out of the many authentication schemes in this paper we are trying to focus on the performance and classification of one of the techniques of authentication that is the biometric authentication. Although efforts of the entire international biometric community, the measurement of accuracy of a biometric system is far to be completely investigated and, eventually, standardized. The paper presents a critical analysis of the measurement of an accuracy and performance of a biometric system.