To obtain access to full text of journal and articles you must register!
- Article name
- Study of the quality of identification of reflex biometrics based on eye micromovements
- Authors
- Tyukin N. Yu., , tiuckin.niu@phystech.edu, Moscow Institute of Physics and Technology (National Research University), Moscow Region, Dolgoprudny, Russia
Ziyatdinova R. R., , ziiatdinova.rr@phystech.edu, Moscow Institute of Physics and Technology (National Research University), Moscow Region, Dolgoprudny, Russia
Novikov Yu. A., , novikov.yua@phystech.edu, Moscow Institute of Physics and Technology (National Research University), Moscow Region, Dolgoprudny, Russia
Oganezyan L. R., , lev@phystech.edu, Moscow Institute of Physics and Technology (National Research University), Moscow Region, Dolgoprudny, Russia
- Keywords
- biometric identification / saccades / eye micromovements / reflex biometrics / prototypical neural network / recognizable and unrecognizable trajectories
- Year
- 2024 Issue 3 Pages 12 - 20
- Code EDN
- VMMWJZ
- Code DOI
- 10.52190/2073-2600_2024_3_12
- Abstract
- Human eye movements reflect a complex interaction between voluntary and involuntary processes associated with vision, cognition, and attention. Individual characteristics of eye movements persist throughout life, making them a promising target for biometric identification. Unlike static biometric characteristics, reflex biometrics based on micro-eye movements are less vulnerable to copying and substitution. This article examines the influence of the type of stimulus trajectories (recognizable and unrecognizable) on the quality of person identification based on eye micromovements. For this purpose, a prototypical neural network was developed, trained on data obtained using an eye tracker. The results show that the best identification performance is achieved when unrecognized trajectories are used for both training and testing the model.
- Text
- BUY for read the full text of article
- Buy
- 500.00 rub
