检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:李苹 LI Ping(Tianjinshi Boyagshitong Technology Co.,Ltd.,Tianjin 300400,China)
机构地区:[1]天津市博洋世通科技有限公司,天津300400
出 处:《信息与电脑》2022年第11期17-19,共3页Information & Computer
摘 要:为提升安防系统人脸识别的速度及质量,营造更加安全、稳定的防护环境,本文对多姿态人脸识别技术在安防系统中的应用展开研究。首先,进行人脸多重检测,并对识别特征模块化提取,布设多姿态识别节点;其次,构建ORL(Olivetti Research Laboratory)多姿态人脸识别模型,采用支持矢量机(Support Vector Machine,SVM)多维姿态处理人脸识别;最后,本文方法与传统单质人脸识别、传统局部人脸识别进行对比实验。测试结果表明:与传统单质人脸识别测试组、传统局部人脸识别测试组相对比,本文分析的多姿态人脸识别测试组最终得出的识别时间仅为0.42 s,表明其实际识别过程中的速度更快,误差小,具有实际的应用价值。In order to improve the speed and quality of face recognition in security systems and create a safer and more stable protection environment,this paper investigates the application of multi-pose face recognition technology in security systems.Firstly,we perform multiple face detection and modular extraction of recognition features,and deploy multi-pose recognition nodes;secondly,we construct an ORL(Olivetti Research Laboratory) multi-pose face recognition model,and use Support Vector Machine(SVM) to process face recognition in multi-dimensional pose;finally,our method Finally,this method is compared with traditional singlequality face recognition and traditional local face recognition.The test results show that compared with the traditional single-quality face recognition test group and the traditional local face recognition test group,the final recognition time of the multi-pose face recognition test group analyzed in this paper is only 0.42 s,which indicates that its actual recognition process is faster and has less error,and has practical application value.
关 键 词:多姿态技术 人脸识别 安防系统 系统应用 识别结构 防护程序
分 类 号:TP391.4[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.30