CASIA OpenIR  > 智能感知与计算研究中心
Combining Data-Driven and Model-Driven Methods for Robust Facial Landmark Detection
Zhang, Hongwen1,2; Li, Qi1; Sun, Zhenan1,2; Liu, Yunfan1
2018-10-01
发表期刊IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
卷号13期号:10页码:2409-2422
文章类型Article
摘要
; Facial landmark detection is an important yet challenging task for real-world computer vision applications. This paper proposes an effective and robust approach for facial landmark detection by combining data-and model-driven methods. First, a fully convolutional network (FCN) is trained to compute response maps of all facial landmark points. Such a data-driven method could make full use of holistic information in a facial image for global estimation of facial landmarks. After that, the maximum points in the response maps are fitted with a pre-trained point distribution model (PDM) to generate the initial facial shape. This model-driven method is able to correct the inaccurate locations of outliers by considering the shape prior information. Finally, a weighted version of regularized landmark mean-shift (RLMS) is employed to fine-tune the facial shape iteratively. This estimation-correction-tuning process perfectly combines the advantages of the global robustness of the data-driven method (FCN), outlier correction capability of the model-driven method (PDM), and non-parametric optimization of RLMS. Results of extensive experiments demonstrate that our approach achieves state-of-the-art performances on challenging data sets, including 300W, AFLW, AFW, and COFW. The proposed method is able to produce satisfying detection results on face images with exaggerated expressions, large head poses, and partial occlusions.
关键词Facial Landmark Detection Face Alignment Fully Convolutional Network Point Distribution Model Weighted Regularized Mean Shift
WOS标题词Science & Technology ; Technology
DOI10.1109/TIFS.2018.2800901
关键词[WOS]ACTIVE APPEARANCE MODELS ; FACE ALIGNMENT ; LOCALIZATION
收录类别SCI
语种英语
项目资助者National Key Research and Development Program of China(2016YFB1001000) ; National Natural Science Foundation of China(61573360 ; 61427811 ; 61702513)
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号WOS:000431895700001
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/20762
专题智能感知与计算研究中心
作者单位1.Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Ctr Res Intelligent Percept & Comp, Inst Automat,Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China
推荐引用方式
GB/T 7714
Zhang, Hongwen,Li, Qi,Sun, Zhenan,et al. Combining Data-Driven and Model-Driven Methods for Robust Facial Landmark Detection[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2018,13(10):2409-2422.
APA Zhang, Hongwen,Li, Qi,Sun, Zhenan,&Liu, Yunfan.(2018).Combining Data-Driven and Model-Driven Methods for Robust Facial Landmark Detection.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,13(10),2409-2422.
MLA Zhang, Hongwen,et al."Combining Data-Driven and Model-Driven Methods for Robust Facial Landmark Detection".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 13.10(2018):2409-2422.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Zhang et al. - Combi(5821KB)期刊论文出版稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang, Hongwen]的文章
[Li, Qi]的文章
[Sun, Zhenan]的文章
百度学术
百度学术中相似的文章
[Zhang, Hongwen]的文章
[Li, Qi]的文章
[Sun, Zhenan]的文章
必应学术
必应学术中相似的文章
[Zhang, Hongwen]的文章
[Li, Qi]的文章
[Sun, Zhenan]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Zhang et al. - Combining Data-driven and Model-driven Methods.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。