Application of Convolutional Neural Networks for Face Anstispoofing

D. V. Pakulich, S. A. Alyamkin

Research output: Contribution to journalArticlepeer-review

Abstract

An increase in the share of computer vision for biometric identification systems and its application as a security measure leads to the growth of falsification attempts. In view of this fact, the number of methods for the automatic detection of such situations also grows. However, similarly to most of the systems using computer vision in different situations, the attack detection precision may decrease in some cases. The submitted paper considers the existing approaches to the detection of spoofing attacks and gives an estimate for their stability under changing date recording conditions.

Translated title of the contributionИспользование свёрточных нейронных сетей для обнаружения подмены лица его изображением
Original languageEnglish
Article number11
Pages (from-to)412-418
Number of pages7
JournalOptoelectronics, Instrumentation and Data Processing
Volume57
Issue number4
DOIs
Publication statusPublished - Jul 2021

Keywords

  • computer vision
  • convolutional neural networks
  • deep neural networks
  • detection of spoofing attacks

OECD FOS+WOS

  • 2.02 ELECTRICAL ENG, ELECTRONIC ENG
  • 1.03 PHYSICAL SCIENCES AND ASTRONOMY

Fingerprint

Dive into the research topics of 'Application of Convolutional Neural Networks for Face Anstispoofing'. Together they form a unique fingerprint.

Cite this