Face Detection With Different Scales Based on Faster R-CNN

doi:10.1109/TCYB.2018.2859482

CORC > 自动化研究所 > 中国科学院自动化研究所 > 精密感知与控制研究中心 > 精密感知与控制

	Face Detection With Different Scales Based on Faster R-CNN
	Wu, Wenqi1,2 ; Yin, Yingjie1,2 ; Wang, Xingang1,2 ; Xu, De1,2
刊名	IEEE TRANSACTIONS ON CYBERNETICS
	2019-11-01
卷号	49 期号:11 页码:4017-4028
关键词	Deep convolutional neural network (DCNN) deep learning face detection Faster R-CNN
ISSN号	2168-2267
DOI	10.1109/TCYB.2018.2859482
通讯作者	Yin, Yingjie(yingjie.yin@ia.ac.cn)
英文摘要	In recent years, the application of deep learning based on deep convolutional neural networks has gained great success in face detection. However, one of the remaining open challenges is the detection of small-scaled faces. The depth of the convolutional network can cause the projected feature map for small faces to be quickly shrunk, and most detection approaches with scale invariant can hardly handle less than 15 x 15 pixel faces. To solve this problem, we propose a different scales face detector (DSFD) based on Faster R-CNN. The new network can improve the precision of face detection while performing as real-time a Faster R-CNN. First, an efficient multitask region proposal network (RPN), combined with boosting face detection, is developed to obtain the human face ROI. Setting the ROI as a constraint, an anchor is inhomogeneously produced on the top feature map by the multitask RPN. A human face proposal is extracted through the anchor combined with facial landmarks. Then, a parallel-type Fast R-CNN network is proposed based on the proposal scale. According to the different percentages they cover on the images, the proposals are assigned to three corresponding Fast R-CNN networks. The three networks are separated through the proposal scales and differ from each other in the weight of feature map concatenation. A variety of strategies is introduced in our face detection network, including multitask learning, feature pyramid, and feature concatenation. Compared to state-of-the-art face detection methods such as UnitBox, HyperFace, FastCNN, the proposed DSFD method achieves promising performance on popular benchmarks including FDDB, AFW, PASCAL faces, and WIDER FACE.
资助项目	National Natural Science Foundation of China[61421004] ; National Natural Science Foundation of China[61573349] ; National Natural Science Foundation of China[61703398] ; National High Technology Research and Development Program of China (863 Program)[2015AA042308]
WOS关键词	POSE ESTIMATION ; LOCALIZATION ; RECOGNITION
WOS研究方向	Automation & Control Systems ; Computer Science
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000476811000016
资助机构	National Natural Science Foundation of China ; National High Technology Research and Development Program of China (863 Program)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/21698]
专题	精密感知与控制研究中心_精密感知与控制
通讯作者	Yin, Yingjie
作者单位	1.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Wu, Wenqi,Yin, Yingjie,Wang, Xingang,et al. Face Detection With Different Scales Based on Faster R-CNN[J]. IEEE TRANSACTIONS ON CYBERNETICS,2019,49(11):4017-4028.
APA	Wu, Wenqi,Yin, Yingjie,Wang, Xingang,&Xu, De.(2019).Face Detection With Different Scales Based on Faster R-CNN.IEEE TRANSACTIONS ON CYBERNETICS,49(11),4017-4028.
MLA	Wu, Wenqi,et al."Face Detection With Different Scales Based on Faster R-CNN".IEEE TRANSACTIONS ON CYBERNETICS 49.11(2019):4017-4028.