面向移动平台人脸检测的FaceYoLo算法

doi:10.11772/j.issn.1001-9081.2019091535

计算机应用 ›› 2020, Vol. 40 ›› Issue (4): 1002-1008.DOI: 10.11772/j.issn.1001-9081.2019091535

面向移动平台人脸检测的FaceYoLo算法

任海培, 李腾

安徽大学电气工程与自动化学院, 合肥 230601

收稿日期:2019-09-05 修回日期:2019-10-12 出版日期:2020-04-10 发布日期:2019-10-28
通讯作者: 李腾
作者简介:任海培(1994-),男,安徽芜湖人,硕士研究生,主要研究方向:模式识别、深度学习;李腾(1980-),男,安徽淮南人,教授,博士,CCF会员,主要研究方向:模式识别、深度学习。
基金资助:
国家重点研发计划项目（2018YFB1305804）；安徽省杰出青年基金资助项目（1908085J25）。

FaceYoLo algorithm for face detection on mobile platform

REN Haipei, LI Teng

School of Electrical Engineering and Automation, Anhui University, Hefei Anhui 230601, China

Received:2019-09-05 Revised:2019-10-12 Online:2020-04-10 Published:2019-10-28
Supported by:
This work is partially supported by the National Key Research and Development Program of China (2018YFB1305804), the Anhui Provincial Outstanding Youth Foundation(1908085J25).

摘要/Abstract

摘要： 针对移动平台上人脸检测实时性不强的问题，提出了一种基于深度学习的FaceYoLo实时人脸检测算法。首先，在YoLov3检测算法的基础上，加入快速消化卷积层（RDCL）缩小输入空间，然后加入多尺度卷积层（MSCL）丰富不同检测尺度的感受野，最后加入中心损失和致密化策略加强模型的泛化能力和鲁棒性。实验结果表明，在GPU上测试时，该算法较YoLov3算法在速度上提高至原来的8倍，每幅图像的处理速度可达0.002 8 s；精度提高了2.1个百分点；在Android平台上测试时，该算法较最好的MobileNet模型在检测速率上从5 frame/s提升到10 frame/s。通过实验结果可知，该算法能有效提高人脸检测在移动平台上的实时性能。

关键词: 卷积神经网络, 人脸检测, 深度学习, 移动平台, Android

Abstract: Concerning the problem of low real-time performance of face detection on mobile platform,a FaceYoLo real-time face detection algorithm based on deep learning was proposed. Firstly,based on the YoLov3 detection algorithm,the Rapidly Digested Convolutional Layers (RDCL) were added to reduce the input space size, then Multiple Scale Convolutional Layers(MSCL)were added to enrich the receptive fields of different detection scales,and finally the central loss and densification strategy were added to strengthen the generalization ability and robustness of the model. The experimental results show that,when tested on the GPU,the proposed algorithm improves the speed by nearly 8 times compared with the YoLov3 algorithm,has the processing time of each image reached 0. 002 8 s,and increases the accuracy by 2. 1 percentage points;when tested on the Android platform,the proposed algorithm has the detection rate increased from 5 frame/s to 10 frame/s compared with the best MobileNet model,demonstrating that the algorithm can effectively improve the real-time performance of face detection on mobile platform.

Key words: Convolutional Neural Network (CNN), face detection, deep learning, mobile platform, Android

中图分类号:

TP391.41

任海培, 李腾. 面向移动平台人脸检测的FaceYoLo算法[J]. 计算机应用, 2020, 40(4): 1002-1008.

REN Haipei, LI Teng. FaceYoLo algorithm for face detection on mobile platform[J]. Journal of Computer Applications, 2020, 40(4): 1002-1008.

参考文献

[1] VIOLA P,JONES M. Rapid object detection using a boosted cascade of simple features[C]//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2001:1-9.
[2] LIAO S,JAIN A K,LI S Z. A fast and accurate unconstrained face detector[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(2):211-223.
[3] SCHMIDHUBER J. Deep learning in neural networks:an overview[J]. Neural Networks,2015,61:85-117.
[4] YOU Q,LUO J,JIN H,et al. Building a large scale dataset for image emotion recognition:the fine print and the benchmark[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence. Palo Alto,CA:AAAI Press,2016:308-314.
[5] REN S,HE K,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.
[6] WANG P,LIN L,SHEN C,et al. Multi-attention network for one shot learning[C]//Proceeding of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:6212-6220.
[7] LIN T Y,GOYAL P,GIRSHICK R,et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(2):318-327.
[8] HOWARD A G,ZHU M,CHEN B,et al. MobileNets:efficient convolutional neural networks for mobile vision applications[EB/OL].[2018-09-20]. https://arxiv.org/pdf/1704.04861.pdf.
[9] KINGMA D P, DHARIWAL P. Glow:Generative flow with invertible 1x1 convolutions[EB/OL].[2019-02-10]. http://papers.nips.cc/paper/8224-glow-generative-flow-with-invertible-1x1-convolutions.pdf.
[10] SIMONVAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2018-05-10]. https://arxiv.org/pdf/1409.1556.pdf.
[11] WANG F,LIU W,LIU W,et al. Additive margin Softmax for face verification[J]. IEEE Signal Processing Letters,2018,25(7):926-930.
[12] LIN T Y,MAIRE M,BELONGIE S,et al. Microsoft COCO:common objects in context[C]//Proceedings of the 2014 European Conference on Computer Vision,LNCS 8693. Cham:Springer, 2014:740-755.
[13] KARPATHY A, LI F. Deep visual-semantic alignments for generating image descriptions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2015:3128-3137.
[14] HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//Proceeding of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:770-778.
[15] GONG C,TAO D,LIU W,et al. Label propagation via teaching-to-learn and learning-to-teach[J]. IEEE Transactions on Neural Networks and Learning Systems,2017,28(6):1452-1465.
[16] ZHANG K,ZHANG Z,LI Z,et al. Joint face detection and alignment using multitask cascaded convolutional networks[J]. IEEE Signal Processing Letters,2016,23(10):1499-1503.
[17] FARFADE S S, SABERIAN M J, LI L J. Multi-view face detection using deep convolutional neural networks[C]//Proceedings of the 5th ACM on International Conference on Multimedia Retrieval. New York:ACM,2015:643-650.
[18] 孙劲光, 孟凡宇. 基于深度神经网络的特征加权融合人脸识别方法[J]. 计算机应用,2016,36(2):437-443. (SUN J G, MENG F Y. Face recognition based on deep neural network and weighted fusion of face features[J]. Journal of Computer Applications,2016,36(2):437-443.)
[19] LIENHART R,MAYDT J. An extended set of Haar-like features for rapid object detection[EB/OL].[2019-02-10]. http://www.staroceans.org/documents/ICIP2002.pdf.
[20] MISHKIN D, SERGIEVSKIY N, MATAS J. Systematic evaluation of convolution neural network advances on the ImageNet[J]. Computer Vision and Image Understanding,2017,161:11-19.
[21] SHELHAMER E,LONG J,DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4):640-651.
[22] 牛连强, 陈向震, 张胜男, 等. 深度连续卷积神经网络模型构建与性能分析[J]. 沈阳工业大学学报,2016,38(6):662-666. (NIU L Q,CHEN X Z,ZHANG S N,et al. Modeling and performance analysis of deep continuous convolutional neural network[J]. Journal of Shenyang University of Technology, 2016,38(6):662-666.)
[23] REN S,HE K,GIRSHICK R,et al. Object detection networks on convolutional feature maps[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(7):1476-1481.
[24] 熊咏平, 丁胜, 邓春华, 等. 基于深度学习的复杂气象条件下海上船只检测[J]. 计算机应用,2018,38(12):3631-3637. (XIONG Y P,DING S,DENG C H,et al. Ship detection under complex sea and weather conditions based on deep learning[J]. Journal of Computer Applications,2018,38(12):3631-3637.)
[25] SHANG W,SOHN K,ALMEIDA D,et al. Understanding and improving convolutional neural networks via concatenated rectified linear units[EB/OL].[2019-02-10]. https://arxiv.org/pdf/1603.05201.pdf.
[26] UIJLINGS J R R,VAN DE SANDE K E A,GEVERS T,et al. Selective search for object recognition[J]. International Journal of Computer Vision,2013,104(2):154-171.
[27] QU Y, LIN L, SHEN F, et al. Joint hierarchical category structure learning and large-scale image classification[J]. IEEE Transactions on Image Processing,2017,26(9):4331-4346.
[28] WEN Y, ZHANG K, LI Z, et al. A discriminative feature learning approach for deep face recognition[C]//Proceedings of the 2016 European Conference on Computer Vision. Cham:Springer,2016:499-515.
[29] LI J,MEI X,PROKHOROV D,et al. Deep neural network for structural prediction and lane detection in traffic scene[J]. IEEE Transactions on Neural Networks and Learning Systems,2017,28(3):690-703.
[30] VASWANI A,SHAZEER N,PARMAR N,et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York:Curran Associates,2017:6000-6010.
[31] GUO Y,ZHANG L,HU Y,et al. MS-Celeb-1M:a dataset and benchmark for large-scale face recognition[C]//Proceedings of the 2016 European Conference on Computer Vision,LNCS 9907. Cham:Springer,2016:87-102.
[32] ZHANG S,ZHU X,LEI Z,et al. FaceBoxes:a CPU real-time face detector with high accuracy[C]//Proceedings of the 2017 IEEE International Joint Conference on Biometrics. Piscataway:IEEE,2017:1-9.
[33] XU K,BA J L,KIROS R,et al. Show,attend and tell:neural image caption generation with visual attention[C]//Proceedings of the 32nd International Conference on International Conference on Machine Learning. New York:Journal of Machine Learning Research,2015:2048-2057.

面向移动平台人脸检测的FaceYoLo算法

FaceYoLo algorithm for face detection on mobile platform

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[2]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[3]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[4]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[5]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[6]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[7]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[8]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[9]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[10]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[11]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[12]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[13]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[14]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[15]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.