首页 | 本学科首页   官方微博 | 高级检索  
     

基于注意力模型的人脸关键点检测算法
引用本文:秦晓飞,盛凯,朱玥,杨勇,赵刚,贾程,李成名,鲁小东,周坚风.基于注意力模型的人脸关键点检测算法[J].光学仪器,2020,42(2):45-49.
作者姓名:秦晓飞  盛凯  朱玥  杨勇  赵刚  贾程  李成名  鲁小东  周坚风
作者单位:上海理工大学 光电信息与计算机工程学院,上海 200093;上海理工大学 机械工程学院,上海 200093;杭州亿美实业有限公司,浙江 杭州 310000;杭州亿美光电科技有限公司,浙江 杭州 310000
基金项目:国家重点研究发展计划(2016YFF0101400)
摘    要:人脸关键点定位因受到表情、光照、姿态等的影响,常常会出现大的误差。为了准确地定位到人脸的关键点,提出了一种基于注意力模型的人脸关键点检测算法。先是利用可变型模型(DPM)算法检测出图片中的人脸区域,然后结合残差网络(ResNet)和收缩激励网络(SeNet)对该区域进行人脸关键点定位。实验结果表明,该算法在人脸数据集上获得了较高的准确率,证明了该算法的有效性。

关 键 词:人脸关键点检测  注意力模型  DPM人脸检测
收稿时间:2019/5/8 0:00:00

Detection algorithm for key points on face based on attention model
QIN Xiaofei,SHENG Kai,ZHU Yue,YANG Yong,ZHAO Gang,JIA Cheng,LI Chengming,LU Xiaodong,ZHOU Jianfeng.Detection algorithm for key points on face based on attention model[J].Optical Instruments,2020,42(2):45-49.
Authors:QIN Xiaofei  SHENG Kai  ZHU Yue  YANG Yong  ZHAO Gang  JIA Cheng  LI Chengming  LU Xiaodong  ZHOU Jianfeng
Affiliation:School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China;School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China;Hangzhou Yimei Industrial Co., Ltd., Hangzhou 310000, China;Hangzhou Yimei Photoelectric Technology Co., Ltd., Hangzhou 310000, China
Abstract:Due to the influence of expressions, illuminations, gestures, etc., large errors often occur when positioning key points of a face. In order to accurately locate the key points of the face, a detection algorithm for key points on a face based on attention mechanism is proposed. Firstly, the deformable part model(DPM) algorithm is used to detect the face region in the picture, and then the focal point of the face is located in the region using ResNet and SeNet. The experimental results show that the algorithm achieves good accuracy on the face dataset, and prove the effectiveness of the algorithm.
Keywords:face key point detection  attention model  DPM face detection
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《光学仪器》浏览原始摘要信息
点击此处可从《光学仪器》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号