Face detection using deep learning: An improved faster RCNN approach

被引：327

作者：

Sun, Xudong ^{[1
]}

Wu, Pengcheng ^{[1
]}

Hoi, Steven C. H. ^{[1
,2
]}

机构：

[1] DeepIR Inc, Beijing, Peoples R China

[2] Singapore Management Univ, Sch Informat Syst, Singapore, Singapore

来源：

NEUROCOMPUTING | 2018年 / 299卷

关键词：

Face detection; Faster RCNN; Convolutional neural networks (CNN); Feature concatenation; Hard negative mining; Multi-scale training;

D O I：

10.1016/j.neucom.2018.03.030

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we present a new face detection scheme using deep learning and achieve the state-of-theart detection performance on the well-known FDDB face detection benchmark evaluation. In particular, we improve the state-of-the-art Faster RCNN framework by combining a number of strategies, including feature concatenation, hard negative mining, multi-scale training, model pre-training, and proper calibration of key parameters. As a consequence, the proposed scheme obtained the state-of-the-art face detection performance and was ranked as one of the best models in terms of ROC curves of the published methods on the FDDB benchmark.

引用

页码：42 / 50

页数：9