Face detection and recognition technology based on EfficientNet and BNNeck

Abstract

Face detection is the premise of face attribute recognition, and face attribute recognition is the deep understanding of the computer to face image features. In the construction and development of modern society, with the continuous development of computer vision technology, identity recognition technology with biometric recognition as the core has been paid attention to, and began to be widely used in face verification, interpersonal interaction, precision delivery and other fields. Therefore, on the basis of understanding the current research status of artificial intelligence technology theory and EfficientNet, BNNeck algorithm design, the paper deeply discusses the neural network as the core of the cascade face detection and recognition technology in the new era. The final results show that the improved cascaded face recognition method proposed in this paper has research value.