Integration of Biometric and Electronic Signatures Using Neural Network Algorithms
CENTRAL ASIAN JOURNAL OF THEORETICAL & APPLIED SCIENCES, (2022)Abstract
This article provides arguments regarding the possibility of using modern methods of pattern recognition in problems of biometric authentication: fuzzy extractors, artificial multilayer neural networks, deep learning methods, as well as convolutional, evolutionary, small, wide, hybrid neural networks. The results of our own research in this area are presented. Two methods are proposed for integrating biometric and electronic signatures based on dynamic signature parameters, as well as face and keyboard handwriting parameters.