基于RetinaFace与FaceNet的动态人脸识别系统设计

doi:10.16180/j.cnki.issn1007-7820.2024.12.012

Abstract

Abstract:

This study proposes a dynamic face recognition system to address the problem of requiring the recognized individual's cooperation in existing static face recognition processes. The system uses the RetinaFace and FaceNet algorithms for dynamic face detection and recognition, respectively, and is optimized for high recognition accuracy and real-time performance. In particular, GhostNet is used as the backbone network for RetinaFace detection, and Adaptive-NMS(Non Max Suppression) non-maximum suppression is used for face bounding box regression. For FaceNet recognition, MobileNetV1 is used as the backbone network, and a joint loss function combining Triplet loss and cross-entropy loss is used for face classification. The optimized algorithm has excellent performance in detection and recognition The improved RetinaFace algorithm achieves detection accuracies of 93.35%, 90.84%, and 80.43% on the WiderFace dataset, with a frame rate of 53 frame·s^-1. For dynamic face detection, the average detection accuracy is 96%, with a frame rate of 21 frame·s^-1. When the FaceNet threshold is set to 1.15, the highest recognition rate is 98.23%. The average recognition accuracy of the dynamic recognition system is 98%, with a frame rate of 20 frame·s^-1. The experimental results demonstrate that the proposed system fully addresses the problem of requiring cooperation from the recognized individual in static face recognition and achieves high recognition accuracy and real-time performance.

Key words: face detection, face recognition, deep learning, RetinaFace, FaceNet, network lightweight, MobileNet, GhostNet

CLC Number:

TP391.41

LI Yunpeng, XI Zhihong. Dynamic Face Recognition System Design Based on RetinaFace and FaceNet[J].Electronic Science and Technology, 2024, 37(12): 79-86.

Figures/Tables 15

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Figure 9.

Table 1.

Figure 10.

Table 2.

Table 3.

Figure 11.

Table 4.

References 20

[1]	刘杰, 孙立民. 深度学习人脸识别技术在考勤系统的应用[J]. 智能计算机与应用, 2020, 10(2):17-22.
	Liu Jie, Sun Limin. Application of deep learning face recognition technology in attendance system[J]. Intelligent Computer and Application, 2020, 10(2):17-22.
[2]	徐恬恬, 席志红. 基于改进GD-HASLR算法的遮挡人脸识别[J]. 电子科技, 2023, 36(6)72-79.
	Xu Tiantian, Xi Zhihong. Face recognition with occlusion based on improved GD-HASLR algorithm[J]. Electronic Science and Technology, 2023, 36(6)72-79.
[3]	张坤. 基于深度学习的非约束条件下人脸识别算法研究[D]. 杭州: 中国计量大学,2018:6-8.
	Zhang Kun. Research on face recognition under unconstrained conditions based on deep learning[D]. Hangzhou: China Jiliang University,2018:6-8.
[4]	倪凯丽. 基于深度学习的不同光照下的人脸识别研究[D]. 北京: 北京邮电大学,2020:12-16.
	Ni Kaili. Research on face recognition under different illumination based on deep learning[D]. Beijing: Beijing University of Posts and Telecommunications,2020:12-16.
[5]	王灵珍, 赖惠成. 基于多任务级联CNN与中心损失的人脸识别[J]. 计算机仿真, 2020, 37(8):398-403.
	Wamg Lingzhen, Lai Huicheng. Face recognition based on multi-task cascade convolution CNN and center loss function[J]. Computer Simulation, 2020, 37(8):398-403.
[6]	Khan A, Sohail A, Zahoora U, et al. A survey of the recent architectures of deep convolutional neural networks[J]. Artificial Intelligence Review, 2020, 53(1):5455-5516.
[7]	吴东东. 基于深度学习的自然场景下多人脸检测与识别[D]. 太原: 山西大学, 2020:24-28.
	Wu Dongdong. Face detection and recognition in natural scenes based on deep learning[D]. Taiyuan: Shanxi University,2020:24-28.
[8]	Deng J, Guo J, Ververas E, et al. Retinaface:Single-shot multi-level face localisation in the wild[C]Online: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2020:5203-5212.
[9]	Wang Y, Wang C, Zhang H, et al. Automatic ship detection based on RetinaNet using multi-resolution Gaofen-3 imagery[J]. Remote Sensing, 2019, 11(5):531-532.
[10]	Kirillov A, Girshick R, He K, et al. Panoptic feature pyramid networks[C]. Long Beach: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2019:6399-6408.
[11]	Zhang J, Wu X, Hoi S C H, et al. Feature agglomeration networks for single stage face detection[J]. Neurocomputing, 2020, 380(10):180-189.
[12]	Huang X, Ge Z, Jie Z, et al. Nms by representative region: Towards crowded pedestrian detection by proposal pairing[C]. Online: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020:10750-10759.
[13]	William I, Rachmawanto E H, Santoso H A, et al. Face recognition using facenet(survey, performance test, and comparison)[C]. Long Beach: The Fourth International Conference on Informatics and Computing,IEEE,2019:1-6.
[14]	葛道辉, 李洪升, 张亮, 等. 轻量级神经网络架构综述[J]. 软件学报, 2020, 31(9):2627-2653.
	Ge Daohui, Li Hongsheng, Zhang Liang, et al. Survey of lightweight neural network[J]. Journal of Software, 2020, 31(9):2627-2653.
[15]	Deng W, Zheng L, Sun Y, et al. Rethinking triplet loss for domain adaptation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 31(1):29-37.
[16]	Han K, Wang Y, Tian Q, et al. Ghostnet:More features from cheap operations[C]. Online: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2020:1580-1589.
[17]	Liu S, Huang D, Wang Y. Adaptive NMS:Refining pedestrian detection in a crowd[C]. Long Beach: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2019:6459-6468.
[18]	Salekin M S, Jelodar A B, Kushol R. Cooking state recognition from images using inception architecture[C]. Long Beach: International Conference on Robotics, Electrical and Signal Processing Techniques,2019: 163-168.
[19]	Yao T, Zhang Q, Wu X, et al. Image recognition method of defective button battery base on improved MobileNetv1[C]. Beijing: Image and Graphics Technologies and Applications(The Fifteenth Chinese Conference), 2020:313-324.
[20]	Pang T, Xu K, Dong Y, et al. Rethinking softmax cross-entropy loss for adversarial robustness[J]. International Conference on Learning Representations, 2019: 5(2):16-35.

算法	Easy AP/%	Medium AP/%	Hard AP/%	FPS /frame·s^-1
Fast-Rcnn	96.38	94.90	89.92	16
MTCNN	85.10	82.36	60.84	26
DSFD	94.61	93.72	88.02	14
RetinaFace_Res	94.92	91.26	80.05	24
RetinaFace_V1	90.16	88.76	70.12	60
本文	93.35	90.84	80.43	53

	视频时长/s	检测时长/s	FPS/frame·s^-1	平均检测精度/%
视频1	25	41	21.4	98.12
视频2	43	57	19.2	98.65
视频3	62	83	18.7	97.33

	AP/%	FAR	最佳门限
Inception+Triplet loss and cls	98.78	0.001	1.16
MobilenetV1+Tripletloss	97.84	0.001	1.15
MobilenetV1+Triplet loss and cls	98.23	0.001	1.15

	视频时长/s	识别时长/s	FPS/ frame·s^-1	平均识别精度/%
视频1	62	75	20	96.24
视频2	46	54	19	95.13
视频3	78	86	21	97.15
视频4	70	81	20	96.38

Dynamic Face Recognition System Design Based on RetinaFace and FaceNet

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 15

References 20

Related Articles 15

Metrics

Comments

Recommended 0

[1]	HE Zhiqiang, SUN Zhanquan. Swin-Transformer-Based Carotid Ultrasound Image Plaque Segmentation [J]. Electronic Science and Technology, 2024, 37(9): 48-56.
[2]	HE Xing, HUANG Yongming, ZHU Yong. Pavement Pothole Detection Method Based on Improved YOLOv5 [J]. Electronic Science and Technology, 2024, 37(7): 53-59.
[3]	YE Yuxin, JU Zhiyong, LAI Ying. Traffic Sign Detection Algorithm Incorporating Receptive Field Enhancement Module and Attention Mechanism [J]. Electronic Science and Technology, 2024, 37(6): 8-16.
[4]	YUAN Ao, QI Jinpeng, JIA Can, XUE Yuxin, GUO Yangyang. A Classification Method of Time Series Pathological Data Segments Based on Deep Learning [J]. Electronic Science and Technology, 2024, 37(6): 84-91.
[5]	ZHU Zihao, SONG Yan. Lightweight Capsule Network Fusing Attention and Capsule Pooling [J]. Electronic Science and Technology, 2024, 37(5): 1-8.
[6]	XIA Rongcheng, LIU Deer. Vehicle Detection and Analysis in Urban Waterlogging Area Based on Deep Learning [J]. Electronic Science and Technology, 2024, 37(5): 18-24.
[7]	LIANG Chenye, ZHANG Xuanxiong. Research on Multiclass Garbage Classification Algorithm Based on Improved MobileNet Network [J]. Electronic Science and Technology, 2024, 37(4): 38-46.
[8]	MA Wenjie, ZHANG Xuanxiong. Research on Blind Roads and Obstacle Recognition Algorithm Based on Deep Learning [J]. Electronic Science and Technology, 2024, 37(3): 75-83.
[9]	CUI Jingnan, HUANG Chunyan, LI Yanling. Improvement of YOLOv5s Algorithm for Steel Surface Defect Detection [J]. Electronic Science and Technology, 2024, 37(12): 48-55.
[10]	LIANG Shuifen, GUO Zhiyong. Advancements of Deep Learning in Imaging Diagnosis of Kidney Stone [J]. Electronic Science and Technology, 2024, 37(12): 67-72.
[11]	LIAN Yue, LIU Deer. Outdoor Navigation for Blind People Dynamic Obstacle Target RGB-D Visual Perception and Detection [J]. Electronic Science and Technology, 2024, 37(12): 9-16.
[12]	XIA Qiangqiang, LI Feifei. Deep Learning with Noisy Labels Based on Co-Teaching [J]. Electronic Science and Technology, 2024, 37(11): 1-6.
[13]	CHENG Jinke, LI Gaolei. Privacy-Preserving Data Style Transfer Method for Artificial Intelligence of Things [J]. Electronic Science and Technology, 2024, 37(10): 1-5.
[14]	JU Ping, SONG Yan, ZHANG Yingjie, XU Yifu, SHAO Hang. Research on Agricultural Crop Diseases and Pests Classification Based on Masked Autoencoding [J]. Electronic Science and Technology, 2024, 37(10): 23-29.
[15]	FENG Ting, YING Jie, YANG Haima, LI Fang. Detection of Cervical Lesions Based on Multi-Scale Features and Attention Mechanism [J]. Electronic Science and Technology, 2024, 37(10): 30-39.