Open AccessBiometric identification and authentication based on a new method of a pulse wave contour forming
Author(s) -
Mikhail S. Gerashchenko,
A G Fateev,
Marina V. Markuleva,
Andrey N. Astafyev,
Sergey L. Zefirov,
Sergey M. Gerashchenko
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1679/2/022017
Subject(s) - biometrics , identification (biology) , computer science , authentication (law) , pulse (music) , feature (linguistics) , set (abstract data type) , artificial neural network , pattern recognition (psychology) , artificial intelligence , key (lock) , data mining , feature vector , feature recognition , computer security , telecommunications , linguistics , philosophy , botany , detector , biology , programming language
The paper considers authentication methods, including biometric. The advantages, disadvantages and limitations of the known authentication methods are considered, and for the first time it is proposed to use hydrocuff pulse wave technology for biometric identification. A parameters set characterizing the pulse wave contour and its derivatives is defined. As the pulse wave mathematical processing result, a multiparametric feature space is formed. The paper considers the main problems that arise when collecting source data. To solve legal and ethical issues, as well as reduce the cost of forming a database, the possibility of applying algorithms for generating synthetic biometric images has been proved. Synthetic biometric images are designed to use neural network technologies for identification and authentication based on the large databases analysis.