基于SSD算法的人脸遮挡检测

2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC) Pub Date : 2020-07-01 DOI:10.1109/ICEIEC49280.2020.9152335

Xu Ziwei, Zhang Liang, Pu Jingyu, Zhang Jinqian, Chen Hongling, Zhang Yiwen, Huang Xi, Xu Siyuan, Yu Haoyang

{"title":"基于SSD算法的人脸遮挡检测","authors":"Xu Ziwei, Zhang Liang, Pu Jingyu, Zhang Jinqian, Chen Hongling, Zhang Yiwen, Huang Xi, Xu Siyuan, Yu Haoyang","doi":"10.1109/ICEIEC49280.2020.9152335","DOIUrl":null,"url":null,"abstract":"In recent years, as an important technology in deep learning, target detection has been widely used in all aspects of life. Aiming at the problem of occlusions in face recognition, this paper adopts SSD (Single Shot MultiBox Detector) deep learning target detection algorithm to classify and locate face occlusions. The average precision of all categories (mAP) reached 95.46% through the self-built data set of 7 types of common face occlusion. Experiments show that this method can effectively detect the face occlusion, which provides a new idea for automatic intelligent face recognition and has a broad application prospect.","PeriodicalId":352285,"journal":{"name":"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Face Occlusion Detection Based on SSD Algorithm\",\"authors\":\"Xu Ziwei, Zhang Liang, Pu Jingyu, Zhang Jinqian, Chen Hongling, Zhang Yiwen, Huang Xi, Xu Siyuan, Yu Haoyang\",\"doi\":\"10.1109/ICEIEC49280.2020.9152335\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In recent years, as an important technology in deep learning, target detection has been widely used in all aspects of life. Aiming at the problem of occlusions in face recognition, this paper adopts SSD (Single Shot MultiBox Detector) deep learning target detection algorithm to classify and locate face occlusions. The average precision of all categories (mAP) reached 95.46% through the self-built data set of 7 types of common face occlusion. Experiments show that this method can effectively detect the face occlusion, which provides a new idea for automatic intelligent face recognition and has a broad application prospect.\",\"PeriodicalId\":352285,\"journal\":{\"name\":\"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)\",\"volume\":\"21 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICEIEC49280.2020.9152335\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICEIEC49280.2020.9152335","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

摘要

近年来，作为深度学习中的一项重要技术，目标检测已广泛应用于生活的方方面面。针对人脸识别中的遮挡问题，本文采用SSD (Single Shot MultiBox Detector)深度学习目标检测算法对人脸遮挡进行分类定位。通过自建的7种普通人脸遮挡数据集，所有类别(mAP)的平均精度达到95.46%。实验表明，该方法能够有效地检测出人脸遮挡，为自动智能人脸识别提供了新的思路，具有广阔的应用前景。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Face Occlusion Detection Based on SSD Algorithm

In recent years, as an important technology in deep learning, target detection has been widely used in all aspects of life. Aiming at the problem of occlusions in face recognition, this paper adopts SSD (Single Shot MultiBox Detector) deep learning target detection algorithm to classify and locate face occlusions. The average precision of all categories (mAP) reached 95.46% through the self-built data set of 7 types of common face occlusion. Experiments show that this method can effectively detect the face occlusion, which provides a new idea for automatic intelligent face recognition and has a broad application prospect.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)

自引率

0.00%

发文量