基于轻量级卷积神经网络的人脸检测算法

doi:10.19678/j.issn.1000-3428.0057249

计算机工程 ›› 2021, Vol. 47 ›› Issue (7): 273-280. doi: 10.19678/j.issn.1000-3428.0057249

基于轻量级卷积神经网络的人脸检测算法

朱灵灵¹, 高超², 陈福才²

1. 郑州大学中原网络安全研究院, 郑州 450000;
2. 中国人民解放军战略支援部队信息工程大学, 郑州 450000

收稿日期:2020-01-16 修回日期:2020-05-29 发布日期:2020-06-09
作者简介:朱灵灵(1995-),女,硕士研究生,主研方向为计算机视觉、图像处理;高超,助理研究员;陈福才,研究员。
基金资助:
国家自然科学基金（61601513）。

Face Detection Algorithm Based on Lightweight Convolutional Neural Network

ZHU Lingling¹, GAO Chao², CHEN Fucai²

1. Zhongyuan Network Security Research Institute, Zhengzhou University, Zhengzhou 450000, China;
2. PLA Strategic Support Force Information Engineering University, Zhengzhou 450000, China

Received:2020-01-16 Revised:2020-05-29 Published:2020-06-09

摘要/Abstract

摘要： 针对人脸检测在移动端应用时面临的移动设备计算能力及存储资源受限等问题，设计一种基于轻量级卷积神经网络的改进人脸检测算法Lightweight-SSH。基于单点无头人脸检测器（SSH）人脸检测算法，采用基于MobileNet的轻量级卷积神经网络对样本数据进行特征提取，减少模型的参数量和计算量，通过在SSH网络的检测模块中引入可变形卷积层，提升卷积神经网络对人脸形变的建模能力。在Wider Face数据集上的实验结果表明，与常用人脸检测算法相比，Lightweight-SSH算法在保证检测精度的前提下，明显降低模型复杂度，并提高了模型检测速度。

关键词: 人脸检测, 可变形卷积, MobileNet网络, 单点无头人脸检测器, Lightweight-SSH算法

Abstract: When deployed to mobile terminals,face detection applications are usually limited by the computing power and storage resources of the devices.To address the problem,an improved face detection algorithm called Lightweight-SSH using lightweight convolutional neural network is proposed. This face detection algorithm is designed based on the Single Stage Headless Face Detector(SSH) algorithm,and employs MobileNet-based lightweight convolutional neural network to extract the features of sample data,reducing the number of parameters and the amount of computation.A deformable convolution layer is introduced into the detection module of the SSH network to improve the ability of the convolutional neural network to model human face deformation.Experimental results on the Wider Face dataset show that,compared with commonly used face detection algorithms,the Lightweight-SSH algorithm significantly reduces model complexity and improves model detection speed while ensuring detection accuracy.

Key words: face detection, deformable convolution, MobileNet, Single Stage Headless Face Detector(SSH), Lightweight-SSH algorithm

中图分类号:

TP391.41

朱灵灵, 高超, 陈福才. 基于轻量级卷积神经网络的人脸检测算法[J]. 计算机工程, 2021, 47(7): 273-280.

ZHU Lingling, GAO Chao, CHEN Fucai. Face Detection Algorithm Based on Lightweight Convolutional Neural Network[J]. Computer Engineering, 2021, 47(7): 273-280.

https://www.ecice06.com/CN/Y2021/V47/I7/273

图/表 11

20210721091902

20210721091906

20210721091909

20210721091913

20210721091916

20210721091919

20210721092853

20210721092857

20210721092900

20210721092903

20210721092906

参考文献

[1] ZHANG K P,ZHANG Z P,LI Z F,et al.Joint face detection and alignment using multi-task cascaded convolutional networks[J].IEEE Signal Processing Letters,2016,23(10):1499-1503.
[2] REN S,HE K,GIRSHICK R,et al.Faster r-CNN:towards real-time object detection with region proposal networks[EB/OL].[2019-12-10].https://arxiv.org/pdf/1506.01497.pdf.
[3] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot MultiBox detecto[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2016:21-37.
[4] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[C]//Proceedings of IEEE NIPS'12.Washington D.C.,USA:IEEE Press,2012:1097-1105.
[5] SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:1-9.
[6] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].[2019-12-10].https://arxiv.org/pdf/1409.1556.
[7] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:770-778.
[8] SZEGEDY C,VANHOUCKE V,IOFFE S,et al.Rethinking the inception architecture for computer vision[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:2818-2826.
[9] IANDOLA F N,HAN S,MOSKEWICZ M W,et al.SqueezeNet:AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size[EB/OL].[2019-12-10].https://arxiv.org/pdf/1602.07360.
[10] HOWARD A G,ZHU M L,CHEN B,et al.MobileNets:efficient convolutional neural networks for mobile vision applications[EB/OL].[2019-12-10].https://arxiv.org/pdf/1704.04861.
[11] DAI J,QI H,XIONG Y,et al.Deformable convolutional networks[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2017:764-773.
[12] NAJIBI M,SAMANGOUEI P,CHELLAPPA R,et al.SSH:single stage headless face detector[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2017:4875-4884.
[13] LIN T Y,DOLLÁR P,GIRSHICK R,et al.Feature pyramid networks for object detection[EB/OL].[2019-12-10].https://arxiv.org/pdf/1612.03144.
[14] FELZENSZWALB P F,GIRSHICK R B,MCALLESTER D,et al.Object detection with discriminatively trained part-based models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9):1627-1645.
[15] 宋超,许道云,秦永彬.分离多路卷积神经网络研究[J].计算机工程,2017,43(6):145-149,157. SONG C,XU D Y,QIN Y B.Research on detached multiple convolutional neural network[J].Computer Engineering,2017,43(6):145-149,157.(in Chinese)
[16] 黄良辉,康祖超,张昌凡,等.基于轻量级卷积神经网络的人脸识别方法[J].湖南工业大学学报,2019,32(2):43-47. HUANG L H,KANG Z C,ZHANG C F,et al.Research on face recognition technology based on lightweight convolutional neural networks[J].Journal of Hunan University of Technology,2019,32(2):43-47.(in Chinese)
[17] 蔡汉明,随玉腾,张镇,等.基于深度可分离卷积神经网络的农作物病害识别方法[J].安徽农业科学,2019,47(11):244-246,252. CAI H M,SUI Y T,ZHANG Z,et al.Crop disease recognition based on depthwise separable convolutional neural network[J].Journal of Anhui Agricultural Sciences 2019,47(11):244-246,252.(in Chinese)
[18] 孙贵华,陈淑荣.一种改进的RefineDet多尺度人脸检测方法[J].电子技术应用,2019,45(8):34-39. SUN G H,CHEN S R.An improved RefineDet multi-scale face detection method[J].Application of electronic technology,2019,45(8):34-39.(in Chinese)
[19] YANG S,LUO P,LOY C C,et al.Wider Face:a face detection benchmark[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:5525-5533.
[20] CAI Z W,FAN Q F,FERIS R S,et al.A unified multi-scale deep convolutional neural network for fast object detection[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2016:354-370.

选择文件类型/文献管理软件名称

选择包含的内容

基于轻量级卷积神经网络的人脸检测算法

Face Detection Algorithm Based on Lightweight Convolutional Neural Network

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	付齐, 谢凯, 文畅, 贺建飚. 遮挡与几何感知模型下的头部姿态估计方法[J]. 计算机工程, 2023, 49(3): 296-303,311.
[2]	秦鹏, 唐川明, 刘云峰, 张建林, 徐智勇. 基于改进YOLOv3的红外目标检测方法[J]. 计算机工程, 2022, 48(3): 211-219.
[3]	李柯, 李邵梅, 吉立新, 刘硕. 基于自注意力胶囊网络的伪造人脸检测方法[J]. 计算机工程, 2022, 48(2): 194-200,206.
[4]	尚佳童, 雷涛, 张栋, 杜晓刚, 翟钰杰. 面向刻蚀图像分割的轻量可变形编解码网络[J]. 计算机工程, 2022, 48(12): 203-211,217.
[5]	刘振国, 李钊, 宋滕滕, 何益智. 结合可变形卷积与双边网格的立体匹配网络[J]. 计算机工程, 2022, 48(12): 241-247,254.
[6]	李富豪, 赵希梅. 基于D-Unet神经网络的鼻腔鼻窦肿瘤分割算法[J]. 计算机工程, 2022, 48(1): 281-287.
[7]	包俊, 刘宏哲. 融合可变形卷积网络的鱼眼图像目标检测[J]. 计算机工程, 2021, 47(4): 248-255.
[8]	喻清挺, 喻维超, 喻国平. 基于改进R-FCN的交通标志检测[J]. 计算机工程, 2021, 47(12): 285-290,298.
[9]	陶施帆, 李玉峰, 黄煜峰, 蓝晓宇. 基于深度残差网络和注意力机制的人脸检测算法[J]. 计算机工程, 2021, 47(11): 276-282.
[10]	连泽宇, 田景文. 基于掩膜生成网络的遮挡人脸检测方法[J]. 计算机工程, 2021, 47(11): 292-297,304.
[11]	黄凤琪, 陈明, 冯国富. 基于可变形卷积的改进YOLO目标检测算法[J]. 计算机工程, 2021, 47(10): 269-275,282.
[12]	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.
[13]	郑伟成, 李学伟, 刘宏哲, 代松银. 基于深度学习的疲劳驾驶检测算法[J]. 计算机工程, 2020, 46(7): 21-29.
[14]	林凯瀚, 赵慧民, 吕巨建, 詹瑾, 刘晓勇, 陈荣军. 基于Mask R-CNN的人脸检测与分割方法[J]. 计算机工程, 2020, 46(6): 274-280.
[15]	翟强, 王陆洋, 殷保群, 彭思凡, 邢思思. 基于尺度自适应卷积神经网络的人群计数算法[J]. 计算机工程, 2020, 46(2): 250-254,261.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于轻量级卷积神经网络的人脸检测算法

Face Detection Algorithm Based on Lightweight Convolutional Neural Network

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献

相关文章 15

编辑推荐

Metrics

本文评价