Face detection using deep learning: An improved faster RCNN approach

NEUROCOMPUTING

卷:299

Article

Sun, Xudong¹  Wu, Pengcheng¹  Hoi, Steven C. H.^1,2 

[1] DeepIR Inc, Beijing, Peoples R China

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

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

DOI  :  10.1016/j.neucom.2018.03.030

来源: Elsevier

【 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.

【 授权许可】

Free