融合多尺度特征的轻量级人脸检测算法

doi:10.16451/j.cnki.issn1003-6059.202206003

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1626 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要受到移动设备计算能力和存储资源受限的局限,设计高效、高精度的人脸检测器是一个开放性的挑战.因此,文中提出融合多尺度特征的轻量级人脸检测算法(Lightweight Face Detection Algorithm with Multi-scale Feature Fusion, LFDMF),摒弃被视为人脸检测核心组件的多级检测结构.首先,利用现有的轻量级主干特征提取网络编码输入图像.然后,利用提出的颈部网络扩张特征图感受野,并将含有不同感受野的多尺度信息融至单级特征图中.最后,利用提出的多任务敏感检测头对该单级特征图进行人脸分类、回归和关键点检测.相比分而治之的人脸检测器,LFDMF精度更高、计算量更少.LFDMF按模型计算量高低可构建3个不同大小的网络,大模型LFDMF-L在Wider Face数据集上性能较优,中等模型LFDMF-M和小模型LFDMF-S以极低的模型参数量和计算量实现可观性能.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	王建
	宋晓宁

关键词 ：人脸检测, 多尺度特征, 单级特征图, 多任务敏感检测头

Abstract：Due to the limitations in computing capacity and storage resources of mobile devices, it is still an open challenge to design an efficient and high-precision face detector. In this paper, a lightweight face detection algorithm with multi-scale feature fusion(LFDMF) is proposed. The multi-level detection structure, regarded as the core component of face detection, is removed. Firstly, the existing lightweight backbone feature extraction network is introduced to encode the input image. Then, the proposed neck network is utilized to expand the receptive field of the feature map, and the multi-scale information with different receptive fields is fused into the one-level feature map. Finally, the proposed multi-task sensitive detector head is employed to perform face classification, regression and key point detection for the one-level feature map. Compared with the face detectors with RetinaFace and DSFD, LFDMF achieves higher accuracy and less computation burden. LFDMF builds three networks of different sizes. The large model, LFDMF-L, is built to achieve the most advanced performance on the Wider Face dataset, while the medium model, LFDMF-M, and the small model, LFDMF-S, achieve impressive performance with a small number of model parameters and less computation.

Key words： Face Detection Multi-scale Feature One-Level Feature Map Multi-task Sensitive Detector Head

收稿日期: 2022-03-14

ZTFLH:

TP 391.4

基金资助:国家自然科学基金项目(No.61876072)资助

通讯作者: 宋晓宁,博士,教授,主要研究方向为模式识别、计算机视觉、生物信息学、机器学习.E-mail:x.song@jiangnan.edu.cn.

作者简介: 王建,硕士研究生,主要研究方向为计算机视觉、目标检测.E-mail:6201924155@stu.jiangnan.edu.cn.

引用本文:

王建, 宋晓宁. 融合多尺度特征的轻量级人脸检测算法[J]. 模式识别与人工智能, 2022, 35(6): 507-515. WANG Jian, SONG Xiaoning. Lightweight Face Detection Algorithm with Multi-scale Feature Fusion. Pattern Recognition and Artificial Intelligence, 2022, 35(6): 507-515.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202206003 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2022/V35/I6/507

[1] ZHANG K P, ZHANG Z P, LI Z F, et al. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks. IEEE Signal Processing Letters, 2016, 23(10): 1499-1503.
[2] ZHANG S F, ZHU X Y, LEI Z, et al. FaceBoxes: A CPU Real-Time Face Detector with High Accuracy // Proc of the IEEE International Joint Conference on Biometrics. Washington, USA: IEEE, 2017. DOI: 10.1109/BTAS.2017.8272675.
[3] ZHANG S F, ZHU X Y, LEI Z, et al. S³fd: Single Shot Scale-Invariant Face Detector // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2017: 192-201.
[4] LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature Pyramid Networks for Object Detection // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 936-944.
[5] LIU S, QI L, QIN H F, et al. Path Aggregation Network for Instance Segmentation // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2018: 8759-8768.
[6] GHIASI G, LIN T Y, LE Q V. NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 7029-7038.
[7] QIAO S Y, CHEN L C, YUILLE A. DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution // Proc of the IEEE/CVF Conference on Computer Vision and Pa-ttern Recognition. Washington, USA: IEEE, 2021: 10208-10219.
[8] DENG J K, GUO J, VERVERAS E, et al. RetinaFace: Single-Shot Multi-level Face Localisation in the Wild // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 5202-5211.
[9] TANG X, DU D K, HE Z Q, et al. PyramidBox: A Context-Assisted Single Shot Face Detector // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 812-828.
[10] LI J, WANG Y B, WANG C A, et al. DSFD: Dual Shot Face Detector // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 5055-5064.
[11] LI J, ZHANG B, WANG Y B, et al. ASFD: Automatic and Scalable Face Detector // Proc of the 29th ACM International Confe-rence on Multimedia. New York, USA: ACM, 2021: 2139-2147.
[12] ZHANG S F, CHI C, LEI Z, et al. RefineFace: Refinement Neural Network for High Performance Face Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(11): 4008-4020.
[13] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 770-778.
[14] LAW H, DENG J. CornerNet: Detecting Objects as Paired Keypoints. International Journal of Computer Vision, 2020, 128(3): 642-656.
[15] DUAN K W, BAI S, XIE L X, et al. CenterNet: Keypoint Triplets for Object Detection // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2019: 6568-6577.
[16] NEWELL A, YANG K Y, DENG J. Stacked Hourglass Networks for Human Pose Estimation // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 483-499.
[17] CHEN Q, WANG Y M, YANG T, et al. You Only Look One-Le-vel Feature // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 13034-13043.
[18] XU Y Y, YAN W, YANG G K,et al. CenterFace: Joint Face Detection and Alignment Using Face as Point. Scientific Progra-mming, 2020. DOI: 10.1155/2020/7845384.
[19] HE K M, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2017: 2980-2988.
[20] CHEN D, HUA G, WEN F, et al. Supervised Transformer Network for Efficient Face Detection // Proc of the European Confe-rence on Computer Vision. Berlin, Germany: Springer, 2016: 122-138.
[21] 李盼盼,王朝立,孙占全.基于注意力机制的多特征融合人脸活体检测.信息与控制, 2021, 50(5): 631-640.
(LI P P, WANG C L, SUN Z Q. Face Liveness Detection Based on Multi-feature Fusion with an Attention Mechanism. Information and Control, 2021, 50(5): 631-640.)
[22] SIMONYAN K, ZISSERMAN A. Very Deep Convolutional Networks for Large-Scale Image Recognition[C/OL]. [2022-03-15]. https://arxiv.org/pdf/1409.1556.pdf.
[23] GUO J, DENG J K, LATTAS A, et al. Sample and Computation Redistribution for Efficient Face Detection[C/OL].[2022-03-15]. https://arxiv.org/pdf/2105.04714.pdf.
[24] LI X, WANG W H, WU L J, et al. Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection[C/OL].[2022-03-15]. https://arxiv.org/pdf/2006.04388.pdf.
[25] ZHENG Z H, WANG P, LIU W, et al. Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression // Proc of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI, 2020: 12993-13000.
[26] YANG S, LUO P, LOY C C, et al. WIDER FACE: A Face Detection Benchmark // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 5525-5533.
[27] CHEN K, WANG J Q, PANG J M, et al. MMDetection: Open MMLab Detection Toolbox and Benchmark[C/OL].[2022-03-15]. https://arxiv.org/pdf/1906.07155v1.pdf.
[28] LIU Y, TANG X, HAN J Y, et al. HAMBox: Delving into Mining High-Quality Anchors on Face Detection // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 13043-13051.
[29] TIAN W X, WANG Z X, SHEN H F, et al. Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision[C/OL].[2022-03-15]. https://arxiv.org/pdf/1811.08557.pdf.
[30] WANG H, LI Z F, JI X, et al. Face R-CNN[C/OL].[2022-03-15]. https://arxiv.org/pdf/1706.01061.pdf.
[31] NAJIBI M, SAMANGOUEI P, CHELLAPPA R, et al. SSH: Single Stage Headless Face Detector // Pro of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2017: 4875-4884.
[32] CHEN D, REN S Q, WEI Y C, et al. Joint Cascade Face Detection and Alignment // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2014: 109-122.
[33] SHEN X H, LIN Z, BRANDT J, et al. Detecting and Aligning Faces by Image Retrieval // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2013: 3460-3467.
[34] VIOLA P, JONES M J. Robust Real-Time Face Detection. International Journal of Computer Vision, 2004, 57(2): 137-154.
[35] KÖSTINGER M, WOHLHART P, ROTH P M, et al. Annotated Facial Landmarks in the Wild: A Large-Scale, Real-World Database for Facial Landmark Localization // Proc of the IEEE International Conference on Computer Vision Workshops. Washington, USA: IEEE, 2011: 2144-2151.