基于AdaBoost算法和皮肤模型的视频人脸检测

Q4 Computer Science

Journal of China Universities of Posts and Telecommunications Pub Date : 2013-08-01 DOI:10.1016/S1005-8885(13)60259-9

Cui-huan DU , Hong ZHU , Li-ming LUO , Jie LIU , Xiang-yang HUANG

{"title":"基于AdaBoost算法和皮肤模型的视频人脸检测","authors":"Cui-huan DU , Hong ZHU , Li-ming LUO , Jie LIU , Xiang-yang HUANG","doi":"10.1016/S1005-8885(13)60259-9","DOIUrl":null,"url":null,"abstract":"<div><p>A real-time method is proposed to detect faces in videos. First it uses frame difference method to extract the motion area. Next the clustering character of skin is used to get the general face area. AdaBoost algorithm is applied to make concrete detection of human face. Finally an improved CamShift algorithm method is used to keep the tracking and improving algorithm speed. The experiments demonstrate the robustness and high speed of the proposed algorithm.</p></div>","PeriodicalId":35359,"journal":{"name":"Journal of China Universities of Posts and Telecommunications","volume":"20 ","pages":"Pages 6-9, 24"},"PeriodicalIF":0.0000,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S1005-8885(13)60259-9","citationCount":"20","resultStr":"{\"title\":\"Face detection in video based on AdaBoost algorithm and skin model\",\"authors\":\"Cui-huan DU , Hong ZHU , Li-ming LUO , Jie LIU , Xiang-yang HUANG\",\"doi\":\"10.1016/S1005-8885(13)60259-9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>A real-time method is proposed to detect faces in videos. First it uses frame difference method to extract the motion area. Next the clustering character of skin is used to get the general face area. AdaBoost algorithm is applied to make concrete detection of human face. Finally an improved CamShift algorithm method is used to keep the tracking and improving algorithm speed. The experiments demonstrate the robustness and high speed of the proposed algorithm.</p></div>\",\"PeriodicalId\":35359,\"journal\":{\"name\":\"Journal of China Universities of Posts and Telecommunications\",\"volume\":\"20 \",\"pages\":\"Pages 6-9, 24\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1016/S1005-8885(13)60259-9\",\"citationCount\":\"20\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of China Universities of Posts and Telecommunications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1005888513602599\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"Computer Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of China Universities of Posts and Telecommunications","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1005888513602599","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Computer Science","Score":null,"Total":0}

引用次数: 20

摘要

提出了一种视频中人脸的实时检测方法。首先采用帧差法提取运动区域;然后利用皮肤的聚类特征得到脸部的总面积。采用AdaBoost算法对人脸进行具体检测。最后采用改进的CamShift算法保持跟踪，提高算法速度。实验证明了该算法的鲁棒性和高速度。

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 detection in video based on AdaBoost algorithm and skin model

A real-time method is proposed to detect faces in videos. First it uses frame difference method to extract the motion area. Next the clustering character of skin is used to get the general face area. AdaBoost algorithm is applied to make concrete detection of human face. Finally an improved CamShift algorithm method is used to keep the tracking and improving algorithm speed. The experiments demonstrate the robustness and high speed of the proposed algorithm.

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

Journal of China Universities of Posts and Telecommunications Computer Science-Information Systems

CiteScore

0.50

自引率

0.00%

发文量

1878