Application of Convolutional Neural Networks for Face Anstispoofing
D. V. Pakulich, Sergey A. Alyamkin · Optoelectronics Instrumentation and Data Processing · 2021
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.