Institutional Repository of Vilnius University
Sufabrikuotų pirštų atspaudų atpažinimas naudojant neuroninius tinklus /
Abstract
dc:descriptionThe widespread use of fingerprint-based identity verification systems has highlighted some security weaknesses. It is well known that the fingerprint verification system can be fooled by providing the electronic capture device (optical, capacitive, etc.) with an artificial copy of the fingerprint made of silicone or gelatine. In this research the application of a transformer model (ViT) network to the problem of fake fingerprint recognition is investigated. The work describes and compares the architectures of convolutional and transformer neural network models using them for binary classification of images. It also describes fingerprint datasets and their processing.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2022
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Ščiupakov, Andrej,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD146242402&prefLang=en_US