CASIA OpenIR
Faceboxes: A CPU real-time and accurate unconstrained face detector
Zhang, Shifeng1,2,3; Wang, Xiaobo1,2,3; Lei, Zhen1,2,3; Li, Stan Z.1,2,3
Source PublicationNEUROCOMPUTING
ISSN0925-2312
2019-10-28
Volume364Pages:297-309
Corresponding AuthorLei, Zhen(zlei@nlpr.ia.ac.cn)
AbstractAlthough tremendous strides have been made in face detection, one of the remaining open issues is to achieve CPU real-time speed as well as maintain high performance, since effective models for face detection tend to be computationally prohibitive. To address this issue, we propose a novel face detector, named FaceBoxes, with superior performance on both speed and accuracy. Specifically, the proposed method has a lightweight yet powerful network that consists of the Rapidly Digested Convolution Layers (RDCL) and the Multiple Scale Convolution Layers (MSCL). The former is designed to enable FaceBoxes to achieve CPU real-time speed, while the latter aims to enrich the features and discretize anchors over different layers to handle faces of various scales. Besides, we propose a new anchor densification strategy to make different types of anchors have the same density on the image, which significantly improves the recall rate of small faces. Finally, we present a Divide and Conquer Head (DCH) to boost the prediction ability of the detection layer using above strategy. As a consequence, the proposed detector runs at 28 FPS on the CPU and 254 FPS using a GPU for VGA-resolution images. Moreover, the speed of FaceBoxes is invariant to the number of faces. We evaluate the proposed method on several face detection benchmarks including AFW, PASCAL face, FDDB, WIDER FACE and achieve state-of-the-art performance among CPU real-time methods. (C) 2019 Elsevier B.V. All rights reserved.
KeywordFace detection CPU real-time Convolutional neural network
DOI10.1016/j.neucom.2019.07.064
WOS KeywordOBJECT DETECTION ; CLASSIFICATION ; NETWORKS ; FEATURES ; CASCADE
Indexed BySCI
Language英语
Funding ProjectChinese National Natural Science Foundation[61876178] ; Chinese National Natural Science Foundation[61806196] ; Chinese National Natural Science Foundation[61872367] ; Chinese National Natural Science Foundation[61572501]
Funding OrganizationChinese National Natural Science Foundation
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000484070700025
PublisherELSEVIER
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/27212
Collection中国科学院自动化研究所
Corresponding AuthorLei, Zhen
Affiliation1.Chinese Acad Sci, Inst Automat, CBSR, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Automat, NLPR, Beijing, Peoples R China
3.Univ Chinese Acad Sci, Beijing, Peoples R China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences;  Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences;  Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Zhang, Shifeng,Wang, Xiaobo,Lei, Zhen,et al. Faceboxes: A CPU real-time and accurate unconstrained face detector[J]. NEUROCOMPUTING,2019,364:297-309.
APA Zhang, Shifeng,Wang, Xiaobo,Lei, Zhen,&Li, Stan Z..(2019).Faceboxes: A CPU real-time and accurate unconstrained face detector.NEUROCOMPUTING,364,297-309.
MLA Zhang, Shifeng,et al."Faceboxes: A CPU real-time and accurate unconstrained face detector".NEUROCOMPUTING 364(2019):297-309.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Shifeng]'s Articles
[Wang, Xiaobo]'s Articles
[Lei, Zhen]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Shifeng]'s Articles
[Wang, Xiaobo]'s Articles
[Lei, Zhen]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Shifeng]'s Articles
[Wang, Xiaobo]'s Articles
[Lei, Zhen]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.