Design of a Facial Recognition System for Power Grid Video Surveillance Based on Deep Learning Algorithms

In recent years, with the extensive application of deep learning methods, face recognition technology has been greatly developed. Aiming at the problem of video surveillance in power network, a video surveillance method based on image processing is proposed. In this paper, an intelligent decision model based on knowledge automatic extraction is studied and optimized. In power network monitoring, face detection and recognition technology based on deep learning is a commonly used face detection and recognition technology, including: face detection, face alignment, face size alignment. Aiming at video surveillance image in power system, a new technology with strong robustness is studied. This new algorithm can solve this problem well. On this basis, a power network monitoring system based on computer vision technology is adopted. Experimental results show that the proposed method can achieve $\mathbf{9 5. 9 \%}$ accuracy and $\mathbf{9 4. 7 \%}$ stability, and can be used in real environment.