Analysis of Real-Time Face-Verification Methods for Surveillance Applications

• Published in: Journal of Imaging Vol. 9; no. 2; p. 21
• Main Authors: Filiberto Perez-Montes, Jesus Olivares-Mercado, Gabriel Sanchez-Perez, Gibran Benitez-Garcia, Lidia Prudente-Tixteco, Osvaldo Lopez-Garcia
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 18.01.2023; MDPI
• Subjects: Cameras; Celebrities; Computer applications to medicine. Medical informatics; Datasets; EfficientNet; Electronic computers. Computer science; Electronic surveillance; face verification; Facial recognition technology; GhostNet; Image processing; Image resolution; Lighting; lightweight face recognition; Machine learning; Methods; MobileFaceNet; Neural networks; Photography; QA75.5-76.95; R858-859.7; Real time; Rotation; Surveillance; TR1-1050; Verification; video surveillance; Mexico; GhostNet; EfficientNet; face verification; MobileFaceNet; video surveillance; lightweight face recognition

In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Con...