MODEL OF THE FACIAL RECOGNITION PROCEDURE MODEL AND THE IRIS OF THE EYE DURING BIOMETRIC AUTHENTICATION OF PERSONNEL OF CRITICAL INFRASTRUCTURE FACILITIES USING NEURAL NETWORK TOOLS.

Abstract

Today's challenges determine the need to improve the means of biometric authentication of personnel of critical infrastructure facilities. Common means of biometric authentication, which are usually based on the use of neural network technologies for facial image analysis, in many cases are not sufficiently adapted to the conditions of recognition during the performance of the personnel's functional duties, which are characterized by the influence of various interferences during video recording and an increase in the probability of attacks using dummies . Another promising direction of improvement is determined by the availability of modern means of video registration, which provide an additional possibility of recognizing a person by the iris of the eye and the possibility of recognizing emotions, which allows assessing the psycho-emotional state of staff representatives. It is shown that the first stage of improving neural network means of biometric authentication is the development of a formalized description of the recognition procedure, which takes into account promising areas of improvement. An appropriate model is proposed that provides a formalized description and criteria for evaluating the effectiveness of each of the operations and the recognition procedure as a whole. At the same time, for the first time, the list of criteria for assessing the quality of pre-processing of images, subject to neural network analysis in the biometric authentication system, has been substantiated, and for the first time, approaches to determining the parameters of interference and recognizing attacks using dummies have been proposed. The approach to determining the parameters of obstacles involves comparing the parameters of obstacles with the location and number of key and control faces that they overlap. Recognition of attacks is proposed to be implemented based on the analysis of the dynamics of basic emotions, the dynamics of eye movement parameters and the environment. The results of this study are important in the context of the development of effective biometric authentication tools, as they provide a formalized description of the requirements for the functionality of the main components of this procedure for recognizing the identity and emotions of personnel of critical infrastructure facilities.