Real time face recognition system based on YOLO and InsightFace

Face Recognition is an important research topics in Machine Learning and Artificial Intelligence. It analyses and compares person's facial traits with a database that contains different faces to automatically recognise and verify a person's identity. It has attracted a lot of attention recently due to its non-intrusive nature. Unlike other biometric identification systems, face recognition does not require physical contact with the individual being identified, making it more convenient and hygienic. Although the existing face recognition system has achieved better performance, recognizing the obscured and disguised faces is difficult. Thus, to deal with these problems, this paper reveals a new real time unique face recognition network called YOLO-InsightFace that combines YOLO-V7, a cutting-edge deep learning model and InsightFace, one-of-a-kind 2D & 3D face analysis python module. YOLO-V7 is highly accurate and fast, making it ideal for real-time applications while InsightFace is capable of recognizing faces by generating highly discriminative face embeddings.