人脸识别技术是如今最热门的领域之一,在新冠肺炎疫情的特殊情况下,出门佩戴口罩是大家共同的责任。为了实现对戴口罩人脸的实时性检测,本文提出了基于YOLOv3的戴口罩人脸识别算法,使用YOLOv3算法来提高识别速度,在OpenCV环境下捕获并识别目标图像。本文对系统进行了实验验证,筛选准确率达到95.5%,动态检测速度高达每秒27帧,满足实时检测标准。

Face recognition technology is one of the hottest fields today,under the special circumstances of this year's epidemic,it is our common responsibility to wear masks when going out.In order to realize the real-time detection of faces wearing masks,a face recognition algorithm with masks based on YOLOv3 is proposed.Use YOLOv3 algorithm to improve the recognition speed,capture and recognize the target image in the OpenCV environment.In this paper,the system has been experimentally verified,and the screening accuracy is 95.5%,and the dynamic detection speed is up to 27 frames per second,which meets the real-time detection standard.