Multi-face detection algorithm suitable for video surveillance

Abstract

With the continuous improvement of urban construction, people's demand for social security has gradually increased. It is an effective method to identify criminals by using face detection technology equipped with city monitoring. In places with dense crowd flow, multiple faces of different sizes will appear, and the face detection algorithm cannot take into account both the detection speed and the detection accuracy. In this paper, by using data augmentation method, redesigning the detection network structure with deep separable convolution, and optimizing the NMS algorithm,the improved MTCNN algorithm is faster than MTCNN algorithm in the application environment of processing multi-face detection .The accuracy rate reaches 92%. At the same time, the output of mtcnn on face qualiy is increased to strengthen the robustness of face detection and improve the recognition accuracy for subsequent face recognition.