期刊文献+

基于Faster R-CNN的人脸识别算法研究 被引量:5

Face recognition algorithm based on Faster R-CNN
下载PDF
导出
摘要 人脸识别技术是身份认证的重要方式。旨在设计算法识别身份证人像与待检人像是否为同一旅客。使用卷积神经网络进行人脸识别算法的研究。使用检测人脸后计算人脸特征间距离的方式进行算法设计,最终达到95%的正确率。结果表明,FasterR-CNN算法能较精准的检测人脸,VGG-Net可以较好地提取人脸特征值,欧式距离可以精确计算人脸特征之间的距离。 Face recognition technology is an important way of identity authentication. The purpose of this paper was to design an algorithm to identify whether the identity witness and the person to be inspected were the same passengers. Face recognition algorithm based on convolutional neural network was studied. The algorithm was designed by calculating the distance between face features after face detection, and the final accuracy was 95%. The results show that Faster R-CNN algorithm can detect face accurately, VGG-Net can extract face feature values well, and Euclidean distance can accurately calculate the distance between face features.
作者 景辉 阎志远 戴琳琳 李贝贝 JING Hui;YAN Zhiyuan;DAI Linlin;LI Beibei(Institute of Computing Technologies, China Academy of Railway Sciences Corporation Limited,Beijing 100081, China)
出处 《铁路计算机应用》 2019年第10期8-11,共4页 Railway Computer Application
基金 中国铁道科学研究院研究开发计划项目(2017YJ096) 中国铁道科学研究院电子所创新基金课题(DZYF17-01)
关键词 卷积神经网络 人脸检测 人脸识别 FasterR-CNN算法 convolutional neural network face detection face recognition
  • 相关文献

参考文献5

二级参考文献23

共引文献159

同被引文献59

引证文献5

二级引证文献28

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部