基于改进Faster?RCNN的自然场景人脸检测

doi:10.19678/j.issn.1000-3428.0056723

摘要/Abstract

摘要： 为实现对自然场景下小尺度人脸的准确检测，提出一种改进的Faster-RCNN模型。采用ResNet-50提取卷积特征，对不同卷积层的特征图进行多尺度融合，同时将区域建议网络产生的锚框由最初的9个改为15个，以更好地适应小尺度人脸检测场景。在此基础上，利用在线难例挖掘算法优化训练过程，采用软非极大值抑制方法解决漏检重叠人脸的问题，并在训练阶段通过多尺度训练提高模型的泛化能力。实验结果表明，该模型在Wider Face数据集上平均精度为89.0%，较原Faster-RCNN模型提升3.5%，在FDDB数据集上检出率也高达95.6%。

关键词: 人脸检测, Faster-RCNN模型, 多尺度融合, 在线难例挖掘, 软非极大值抑制

Abstract: To realize accurate detection of small-scale faces in natural scene,this paper constructs an improved Faster-RCNN model.The model uses ResNet-50 to extract convolution features,and performs multi-scale fusion for feature maps of different convolutional layers.At the same time,the number of Anchors generated by the Regional Proposal Network(RPN) has been changed from 9 to 15 to better adapt to the small-scale face detection scenes.On this basis,the Online Hard Example Mining(OHEM) algorithm is used to optimize the training process.Soft-Non-Maximum Suppression(Soft-NMS) method is used to reduce the missed detection of overlapping faces,and in the training phase the multi-scale training method is adopted to improve the generalization ability of the model.Experimental results show that the average precision of the proposed model is 89.0% on the Wider Face dataset,which is 3.5% higher than that of the original Fast-RCNN model.The relevance ratio of the proposed model reaches 95.6% on the FDDB dataset.

Key words: face detection, Faster-RCNN model, multi-scale fusion, Online Hard Example Mining(OHEM), Soft-Non-Maximum Suppression(Soft-NMS)

中图分类号:

TP391

李祥兵, 陈炼. 基于改进Faster?RCNN的自然场景人脸检测[J]. 计算机工程, 2021, 47(1): 210-216.

LI Xiangbing, CHEN Lian. Face Detection in Natural Scene Based on Improved Faster-RCNN[J]. Computer Engineering, 2021, 47(1): 210-216.

https://www.ecice06.com/CN/Y2021/V47/I1/210

图/表 6

20210125164347

20210125164351

20210125164354

20210125164358

20210125164401

20210125164404

参考文献

[1] VIOLA P,JONES J.Rapid object detection using a boosted cascade of simple features[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2001:511-518.
[2] VIOLA P,JONES J.Robust real-time face detection[J].International Journal of Computer Vision,2004,57(2):137-154.
[3] ZHU Q,YEH M C,CHENG K T,et al.Fast human detection using a cascade of histograms of oriented gradients[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2006:1491-1498.
[4] LI Jianguo,ZHANG Yimin.Learning SURF cascade for fast and accurate object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:3468-3475.
[5] ZHANG Zemiao,HUO Huan,ZHAO Fengyu.Survey of object detection algorithm based on deep convolutional neural networks[J].Journal of Chinese Computer Systems,2019,40(9):1825-1831.(in Chinese)张泽苗,霍欢,赵逢禹.深层卷积神经网络的目标检测算法综述[J].小型微型计算机系统,2019,40(9):1825-1831.
[6] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:580-587.
[7] CHEN Dong,HUA Gang,WEN Fang,et al.Supervised transformer network for efficient face detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:122-138.
[8] LE T H N,ZHANG Y,ZHU C,et al.Multiple scale Faster-RCNN approach to driver's cell-phone usage and hands on steering wheel detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:46-53.
[9] DAI Haineng,MAO Yaobin.An improved face detection algorithm based on R-FCN model[J].Computer and Modernization,2018,276(8):16-19,24.(in Chinese)戴海能,茅耀斌.一种改进的基于R-FCN模型的人脸检测算法[J].计算机与现代化,2018,276(8):16-19,24.
[10] REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[11] TANG Tianyu,ZHOU Shilin,DENG Zhipeng,et al.Vehicle detection in aerial images based on region convolutional neural networks and hard negative example mining[J].Sensors,2017,17(2):336.
[12] BODLA N,SINGH B,CHELLAPPA R,et al.Soft-NMS-improving object detection with online of code[C]//Proceedings of 2017 IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2017:5562-5570.
[13] YANG Bin,YAN Junjie,LEI Zhen,et al.Aggregate channel features for multi-view face detection[C]//Proceedings of IEEE International Joint Conference on Biometrics.Washington D.C.,USA:IEEE Press,2014:1-8.
[14] ZHANG Lun,CHU Rufeng,XIANG Shiming,et al.Face detection based on multi-block LBP representation[C]//Proceedings of International Conference on Biometrics.Berlin,Germany:Springer,2007:11-18.
[15] BOURDEV L,BRANDT J B.Robust object detection via soft cascade[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2005:236-243.
[16] LI S Z,ZHU L,ZHANG Z Q.Statistical learning of multi-view face detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2002:67-81.
[17] YAN Junjie,LEI Zhen,WEN Longyin.The fastest deformable part model for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:2497-2504.
[18] FELZENSZWALB P F,GIRSHICK R B,MCALLESTER D,et al.Object detection with discriminatively trained part-based models[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2010:1627-1645.
[19] LI Haoxiang,LIN Zhe,SHEN Xiaohui.A convolutional neural network cascade for face detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:5325-5334.
[20] ZHANG Kaipeng,ZHANG Zhanpeng,LI Zhifeng.Joint face detection and alignment using multitask cascaded convolutional networks[J].IEEE Signal Processing Letters,2016,23(10):1499-1503.
[21] UIJLINGS J R,VANDESANDE K E,GEVERS T,et al.Selective search for object recognition[J].International Journal of Computer Vision,2013,104(2):154-171.
[22] DAI Jifeng,LI Yi,HE Kaiming,et al.R-FCN:object detection via region-based fully convolutional networks[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems.New York,USA:ACM Press,2016:379-387.
[23] WAN Shaohua,CHEN Zhijun,ZHANG Tao,et al.Bootstrapping face detection with hard negative examples[EB/OL].(2016-08-07)[2019-10-10].https://arxiv.org/pdf/1608.02236.pdf.
[24] WANG Yitong,JI Xing,ZHOU Zheng,et al.Detecting faces using region-based fully convolutional networks[EB/OL].(2017-09-18)[2019-10-10].https://www.researchgate.net/publication/319875564_Detecting_Faces_Using_Region-based_Fully_Convolutional_Networks#read.
[25] CHEN Ze,YE Xueyi,QIAN Dingwei,et al.Small-scale pedestrian detection using improved Faster R-CNN network[J].Computer Engineering,2020,46(9):226-232,241.(in Chinese)陈泽,叶学义,钱丁炜,等.基于改进Faster R-CNN的小尺度行人检测[J].计算机工程,2020,46(9):226-232,241.
[26] CHEN X L,GUPTA A.An implementation of Faster RCNN with study for region sampling[EB/OL].(2017-02-08)[2019-10-10].https://arxiv.org/pdf/1702.02138.pdf.
[27] ZHUANG Fuzhen,LUO Ping,HE Qing,et al.Research progress on transfer learning[J].Journal of Software,2015,26(1):26-39.(in Chinese)庄福振,罗平,何清,等.迁移学习研究进展[J].软件学报,2015,26(1):26-39.
[28] RUSSAKOVSKY O,DENG J,SU H,et al.ImageNet large scale visual recognition challenge[J].International Journal of Computer Vision,2015,115(3):211-252.
[29] CHEN Dong,REN Shaoqing,WEI Yichen,et al.Joint cascade face detection and alignment[C]//Proceedings of the 13th European Conference on Computer Vision.Berlin,Germany:Springer,2014:109-122.

选择文件类型/文献管理软件名称

选择包含的内容