HE Yumin， WANG Zhaohui， GUO Siyu， YAO Shipeng， HU Xiangyang
（School of Mechanical and Electrical Engineering, Xi’an University of Architecture and Technology, Xi’an 710055, China）
Abstract： To automatically detecting whether a person is wearing mask properly, we propose a face mask detection algorithm based on hue-saturation-value (HSV)+histogram of oriented gradient (HOG) features and support vector machines (SVM). Firstly, human face and five feature points are detected with RetinaFace face detection algorithm. The feature points are used to locate to mouth and nose region, and HSV+HOG features of this region are extracted and input to SVM for training to realize detection of wearing masks or not. Secondly, RetinaFace is used to locate to nasal tip area of face, and YCrCb elliptical skin tone model is used to detect the exposure of skin in the nasal tip area, and the optimal classification threshold can be found to determine whether the wear is properly according to experimental results. Experiments show that the accuracy of detecting whether mask is worn can reach 97.9%, and the accuracy of detecting whether mask is worn correctly can reach 87.55%, which verifies the feasibility of the algorithm.
Key words： hue-saturation-value (HSV) features； histogram of oriented gradient (HOG) features； support vector machine (SVM)； face mask detection； feature point detection
References
［1］XIAO W J, GAO Q, JIN K, et al. Investigation of an epidemic cluster caused by COVID-19 cases in incubation period in Shanghai. Chinese Journal of Epidemiology, 2020, 41(9)： 1401-1405.
［2］QI R, JIA R S, XU Z F, et al. Lightweight object detection network based on YOLOV3. Computer Applications and Software, 2020, 37(10)： 208-213.
［3］WANG L H, YANG J W, ZHANG Y H, et al. Tool wear condition recognition based on SDAE. China Mechanical Engineering, 2018, 29(17)： 2038-2045.
［4］GAI S, WANG J S. Image raindrop algorithm research using nonlocal attention enhanced network based on deep learning. Acta Electronica Sinica, 2020, 48(10)： 1899-1908.
［5］ZOU B H, QIN Y T, YUAN X B, et al. Research on mask face detection based on lightweight CNN. Computer Engineering & Software, 2020, 41(8)： 186-188.
［6］LIU L, SUN L J, WANG W J. Classification of fluorescent images in high-throughput dPCR gene chips based on SVM. Packaging Engineering, 2020, 41(19)： 223-229.
［7］MA C, YUAN T, YAO X F, et al. Study on image recognition method of rice disease in field based on HOG+SVM. Acta Agriculturae Shanghai, 2019, 35(5)： 131-136.
［8］SHI L L, WANG X, SHEN Y L. Research on 3D face recognition method based on LBP and SVM. Optik, 2020, 220: 165157.
［9］HU S X, CHANG Y C, YANG J, et al. Multi-target tracking algorithm for highway vehicles based on multi-feature fusion. Automobile Technology, 2020(9)： 8-13.
［10］CHENG K Y, SHI W X, ZHOU B W, et al. Robust KCF pedestrian tracking method with complex scene. Journal of Nanjing University of Aeronautics & Astronautics, 2019, 51(5)： 625-635.
［11］XIAO J J. MAskedface detection and standard wearing mask recognition based on YOLOv3 and YCrCb. Computer Engineering & Software, 2020, 41(7)： 164-169.
［12］XIA S L. Research on driver distraction recognition method based on deep learning. Beijing： China University of Mining and Technology, 2020.
［13］HAN Y J, HAHN H S. Vehicle detection in still images by using boosted local feature detector. Journal of Measurement Science and Instrumentation, 2010, 1(1)： 41-45.
［14］DALAL N, TRIGGS B. Histograms of oriented gradients for human detection//IEEE Computer Socienty Conference on Computer Vision and Pattern Recognition, Jun. 20-25, 2005, San Diego, CA, USA. New York: IEEE, 2005： 886-893.
［15］CORTES C, VAPNIK V. Support-vector networks. Machine Learning, 1995, 20(3)： 273-297.
［16］HSU R L, ABDEL M M， JAIN A K. Face detection in color images. IEEE Transactions on Pattern Analysis and MAchine lntelligence, 2002, 24(5)： 696-706.
基于HSV+HOG特征和SVM的人脸口罩检测算法研究
何育民， 汪朝辉， 郭思宇， 姚世鹏， 胡象洋
（西安建筑科技大学 机电工程学院， 陕西 西安 710055）
摘要:为自动检测人脸是否规范佩戴口罩， 提出了一种基于HSV+HOG特征和SVM的人脸口罩检测算法。 首先， 使用人脸检测算法RetinaFace检测出人脸和五个特征点坐标， 在人脸上使用特征点定位到口鼻区域， 提取该区域的HSV+HOG特征并使用SVM进行训练， 实现对有无佩戴口罩的检测。 然后， 使用RetinaFace把检测目标定位到人脸的鼻尖区域， 使用YCrCb椭圆肤色模型检测鼻尖区域皮肤的暴露情况， 根据实验结果找到最佳分类阈值来判断佩戴是否规范。 实验表明， 该算法的口罩佩戴检测准确率可达97.9%， 佩戴规范检测准确率可达87.55%。
关键词:色相饱和度值特征； 方向梯度直方图特征； 支持向量机； 人脸口罩检测； 特征点检测
引用格式：HE Yumin， WANG Zhaohui， GUO Siyu， et al． Face mask detection algorithm based on HSV+HOG features and SVM． Journal of Measurement Science and Instrumentation， 2022， 13（3）： 267-275. DOI： 10．3969／j．issn．1674-8042．2022．03．003
[full text view]
