Faceboxes: A CPU real-time and accurate unconstrained face detector
文献类型：期刊论文
| 作者 | Zhang, Shifeng1,2,3 ; Wang, Xiaobo1,2,3; Lei, Zhen1,2,3; Li, Stan Z.1,2,3
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2019-10-28 |
| 卷号 | 364页码:297-309 |
| 关键词 | Face detection CPU real-time Convolutional neural network |
| ISSN号 | 0925-2312 |
| DOI | 10.1016/j.neucom.2019.07.064 |
| 通讯作者 | Lei, Zhen(zlei@nlpr.ia.ac.cn) |
| 英文摘要 | Although 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. |
| WOS关键词 | OBJECT DETECTION ; CLASSIFICATION ; NETWORKS ; FEATURES ; CASCADE |
| 资助项目 | Chinese National Natural Science Foundation[61876178] ; Chinese National Natural Science Foundation[61806196] ; Chinese National Natural Science Foundation[61872367] ; Chinese National Natural Science Foundation[61572501] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000484070700025 |
| 出版者 | ELSEVIER |
| 资助机构 | Chinese National Natural Science Foundation |
| 源URL | [http://ir.ia.ac.cn/handle/173211/27211]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心 |
| 通讯作者 | Lei, Zhen |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, NLPR, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, CBSR, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China |
| 推荐引用方式 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. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。