| 基于RetinaFace的人脸多属性检测算法研究 |
| |
| 引用本文： | 随玉腾,阎志远,戴琳琳,景辉. 基于RetinaFace的人脸多属性检测算法研究[J]. 铁路计算机应用, 2021, 30(3): 1-4 |
| |
| 作者姓名： | 随玉腾 阎志远 戴琳琳 景辉 |
| |
| 作者单位： | 1.北京经纬信息技术有限公司，北京 100081 |
| |
| 基金项目： | 中国国家铁路集团有限公司科技研究开发计划课题（N2019X016） |
| |
| 摘 要： | 为提高铁路刷脸检票业务中人脸检测的平均精度,通过研究分析人脸检测算法RetinaFace,针对闸机应用场景制定损失函数,提出了一种基于RetinaFace的人脸多属性检测算法,实现了人脸框位置、人脸是否佩戴墨镜以及人脸遮挡程度等信息的准确输出.算法使用轻量化骨干网络MobileNet-0.25网络结构,移除非必要的分支...
|
| 关 键 词： | 遮挡识别 损失函数 特征金字塔 卷积神经网络 目标检测 |
| 收稿时间： | 2020-11-17 |
Face multi-attribute detection algorithm based on RetinaFace |
| |
| Affiliation: | 1.Beijing Jingwei Information Technology Co. Ltd., Beijing 100081, China2.Institute of Computing Technologies, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China |
| |
| Abstract: | In order to improve the average accuracy of face detection in railway face brushing and ticket checking, this paper proposed a face multi-attribute detection algorithm based on RetinaFace by studying and analyzing the face detection algorithm retinaface and formulating the loss function according to the application scene of the gate. It was implemented the accurate output of the information such as the face frame position, whether the face was wearing sunglasses, and the degree of occlusion. The algorithm used the lightweight backbone network MobileNet-0.25 network structure, and removed unnecessary branches to reduce the computational cost. The detection rate of the algorithm on the railway standard face occlusion data set reached 95.4%, and the recognition accuracy of different occlusion degrees reached 99.2%. |
| |
| Keywords: | |
|
| 点击此处可从《铁路计算机应用》浏览原始摘要信息 |
|
点击此处可从《铁路计算机应用》下载免费的PDF全文 |
|
