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.
Key words
face detection /
mask recognition /
YOLOv3 algorithm /
OpenCV
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1] 吴振.嵌入式平台下戴口罩的人脸识别研究[J].电脑知识与技术,2020,16(30):228-229.
[2] 王兵,李文璟,唐欢.改进YOLO v3算法及其在安全帽检测中的应用[J].计算机工程与应用,2020,56(9):33-40.
[3] 罗元,王薄宇,陈旭.基于深度学习的目标检测技术的研究综述[J].半导体光电,2020,41(1):1-10.
[4] 李晶,黄山.基于YOLOv3目标跟踪方法[J].电光与控制,2019,26(10):87-93.
[5] 阮激扬.基于YOLO的目标检测算法设计与实现[D].北京:北京邮电大学,2019.
[6] 鞠默然,罗海波,王仲博,等.改进的YOLO V3算法及其在小目标检测中的应用[J].光学学报,2019,39(7):253-260.
[7] 施辉,陈先桥,杨英.改进YOLO v3的安全帽佩戴检测方法[J].计算机工程与应用,2019,55(11):213-220.
[8] 朱超平,杨艺.基于YOLO2和ResNet算法的监控视频中的人脸检测与识别[J].重庆理工大学学报(自然科学版),2018,32(8):170-175.