Relative coordinates constraint for face alignment

doi:10.1016/j.neucom.2017.12.071

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	Relative coordinates constraint for face alignment
	Nian, Fudong 2; Li, Teng 4; Bao, Bing-Kun 1; Xu, Changsheng 3
刊名	NEUROCOMPUTING
	2020-06-28
卷号	395 页码:119-127
关键词	Face alignment Relative coordinates constraint CNN Loss function design
ISSN号	0925-2312
DOI	10.1016/j.neucom.2017.12.071
通讯作者	Bao, Bing-Kun(bingkunbao@njput.edu.cn)
英文摘要	We present a practical approach to improve the precision of face alignment for a single image. Recently, face alignment is deemed as a regression problem, and convolutional neural networks (CNNs) or recurrent neural networks (RNNs) are utilized to predict the coordinates of facial landmarks. However, most existing methods only adopt Euclidean loss as the optimization target for each landmark, and neglect the correlations between them, which we think may be inappropriate. To address this issue, in this paper, we introduce a novel Relative Coordinates Constraint (RCC) loss function for face alignment, which considers the relative coordinates between any pairs of landmarks as a new supervision signal. More importantly, we prove that the proposed RCC loss function is trainable and can be easily incorporated in existing CNNs optimization procedure. With the joint supervision of Euclidean loss and RCC loss, we train a robust and light CNNs framework for face alignment. Extensive experimental results on several datasets show that the precision of face alignment improved significantly by the proposed RCC loss and quantitative results are comparable to state-of-the-art methods (mean error 5.39 on 300-W and 6.99 on AFLW). In addition, the proposed framework is also an efficient solution (300 FPS on CPU). We share the implementation code of our proposed methods at https://github.com/nianfudong/RCC-loss. (C) 2019 Elsevier B.V. All rights reserved.
资助项目	National Natural Science Foundation of China[61572503] ; National Natural Science Foundation of China[61572029] ; National Natural Science Foundation of China[61872424] ; National Natural Science Foundation of China[61930 00388] ; National Natural Science Foundation of China[6190070645] ; National Key R&D Program of China[2018YFB1305804] ; Scientific Research Development Foundation of Hefei University[19ZR15ZDA] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039] ; NUPTSF[NY218001] ; Talent Research Foundation of Hefei University[16-17RC23] ; Talent Research Foundation of Hefei University[18-19RC54] ; Open fund for Discipline Construction, Institute of Physical Science and Information Technology, Anhui University
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000536809600012
资助机构	National Natural Science Foundation of China ; National Key R&D Program of China ; Scientific Research Development Foundation of Hefei University ; Key Research Program of Frontier Sciences, CAS ; NUPTSF ; Talent Research Foundation of Hefei University ; Open fund for Discipline Construction, Institute of Physical Science and Information Technology, Anhui University
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/39564]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者	Bao, Bing-Kun
作者单位	1.Nanjing Univ Posts & Telecommun, Coll Telecommun & Informat Engn, Nanjing, Peoples R China 2.Hefei Univ, Hefei, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Anhui Univ, Hefei, Peoples R China
推荐引用方式 GB/T 7714	Nian, Fudong,Li, Teng,Bao, Bing-Kun,et al. Relative coordinates constraint for face alignment[J]. NEUROCOMPUTING,2020,395:119-127.
APA	Nian, Fudong,Li, Teng,Bao, Bing-Kun,&Xu, Changsheng.(2020).Relative coordinates constraint for face alignment.NEUROCOMPUTING,395,119-127.
MLA	Nian, Fudong,et al."Relative coordinates constraint for face alignment".NEUROCOMPUTING 395(2020):119-127.