2020/11/04 by Vecino, Biel Tura, Cobos, Martí, Salembier, Philippe
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
paper · doi:10.48550/arxiv.2011.02222
This article explores a face recognition alternative which seeks to contribute to resolve current security vulnerabilities in most recognition architectures. Current low cost facial authentication software in the market can be fooled by a printed picture of a face due to the lack of depth information. The presented software creates a depth map of the face with the help of a stereo setup, offering a higher level of security than traditional recognition programs. Analysis of the person's identity and facial depth map are processed through deep convolutional neural networks, providing a secure low cost real-time face authentication method.