[1]何 翔.基于 YOLOV5 人脸关键点检测方法的研究与改进[J].计算机技术与发展,2022,32(S1):31-35.[doi:10. 3969 / j. issn. 1673-629X. 2022. S1. 007]
　HE Xiang.Research and Improvement on Facial Landmark Localization Based on YOLOV5[J].,2022,32(S1):31-35.[doi:10. 3969 / j. issn. 1673-629X. 2022. S1. 007]
点击复制

基于 YOLOV5 人脸关键点检测方法的研究与改进()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年S1期
页码:
31-35
栏目:
图形与图像
出版日期:
2022-12-11

文章信息/Info

Title:
Research and Improvement on Facial Landmark Localization Based on YOLOV5
文章编号:
1673-629X(2022)S1-0031-05
作者:
何 翔
南京理工大学 计算机学院,江苏 南京 210000
Author(s):
HE Xiang
School of Computer Science,Nanjing University of Technology,Nanjing 210000,China
关键词:
人脸检测; YOLOV5; 深度学习; 面部关键点定位; RetinaFace
Keywords:
face detection; YOLOV5; deep learning; facial landmark localization; RetinaFace
分类号:
TP18
DOI:
10. 3969 / j. issn. 1673-629X. 2022. S1. 007
摘要:
人脸检测作为人脸信息处理的首要且不可或缺的环节,被广泛应用到人脸对齐、活体检测、人脸识别、人机交互以及人脸超分辨率重建等研究领域,其结果直接影响后续任务的可行性,对人脸信息处理具有重要的研究价值。 人脸检测的研究已经取得了突破性进展,但由于复杂环境包含光照、遮挡、面部角度以及图像分辨率等不确定因素,其仍有性能优化空间。 提出一种基于 YOLOV5 的改进算法,为人脸检测提供面部关键点分支,该分支对面部细节的精准定位起到了重要作用。 实验结果表明该算法在测试集上取得了良好的精度,并适用于实时性人脸检测。
Abstract:
As the primary and indispensable part of face information processing,face detection is widely used in research fields such asface alignment,vivo detection,face recognition,human - computer interaction,and face super - resolution reconstruction. The results offace detection can directly affect the feasibility of successor tasks, which has important research value for the processing of faceinformation. Nowadays,the research of face detection in single environment has made breakthrough progress. However,face detectioncan be further improved by investigating complex environment factors,such as changes in illumination,occlusion,facial angles,and imageresolution,etc. The improved algorithm based on YOLOV5 provides the branch of landmark localization for face detection,which playsan important role in accurate location of facial details. The results of the experiment show that the proposed algorithm achieves highaccuracy in the test set and is suitable for real-time application.

相似文献/References:

[1]李宏伟 陶亮.复杂背景不同光照条件下彩色图像中人脸检测[J].计算机技术与发展,2009,(02):52.
　LI Hong-wei,TAO Liang.Face Detection in Complicated Backgrounds and Different Illumination Conditions of Color Images[J].,2009,(S1):52.
[2]俞扬信 严云洋.视频序列中的人脸检测与定位算法研究[J].计算机技术与发展,2009,(02):109.
　YU Yang-xin,YAN Yun-yang.Algorithm Study of Face Detection and Location in Video Sequence[J].,2009,(S1):109.
[3]金燕 陶亮.基于人眼定位的人脸检测与归一化算法[J].计算机技术与发展,2009,(04):95.
　JIN Yan,TAO Liang.Face Detection and Normalization Based on Localization of Human Eyes[J].,2009,(S1):95.
[4]佘九华 王敬东 李鹏.基于Camshift的人脸跟踪算法[J].计算机技术与发展,2008,(09):12.
　SHE Jiu-hua,WANG Jing-dong,LI Peng.Face Tracking Algorithm Based on Camshift[J].,2008,(S1):12.
[5]李启娟 李金屏.基于轮廓信息的人脸检测[J].计算机技术与发展,2008,(09):108.
　LI Qi-juan,LI Jin-ping.Face Detection Based on Contour Information[J].,2008,(S1):108.
[6]陈伟琦 梁一川 易强 秦文虎.基于肤色和Adaboost算法的人脸检测研究[J].计算机技术与发展,2008,(12):44.
　CHEN Wei-qi,LIANG Yi-chuan,YI Qiang,et al.Face Detection Based on Skin Color and Adaboost Arithmetic[J].,2008,(S1):44.
[7]贾灵芝 李岚 钱坤喜.基于自适应光线补偿的人脸检测算法[J].计算机技术与发展,2008,(12):120.
　JIA Ling-zhi,LI Lan,QIAN Kun-xi.Face Detection Algorithm Based on Self- adaptive Light Compensation[J].,2008,(S1):120.
[8]袁芬萍 季桂树.基于SVM的三阶段人脸检测方法的研究与应用[J].计算机技术与发展,2007,(09):133.
　YUAN Fen-ping,JI Gui-shu.Research and Application about Three- Stage Face Detection Method Based on SVM[J].,2007,(S1):133.
[9]王晶 杨煜.基于边缘方向直方图的Adaboost人脸检测[J].计算机技术与发展,2007,(12):5.
　WANG Jing,YANG Yu.Adaboost for Face Detection Based on Edge Orientation Histograms[J].,2007,(S1):5.
[10]邵平 杨路明 曾耀荣.计算旋转Harr型特征的积分图像算法改进[J].计算机技术与发展,2006,(11):146.
　SHAO Ping,YANG. Lu-ming,ZENG Yao-rong.An Improved Algorithm of Integral Image for Computing Rotated Harr- Like Features[J].,2006,(S1):146.

更新日期/Last Update: 2022-06-10