人脸识别视频分析的设计与实现  

Design and Implementation of Face Recognition in Video Analysis

作　　者：李军[1] 范权昌 蒙仕格 

机构地区：[1]广东技术师范学院,广州510665

出　　处：《现代计算机（中旬刊）》2014年第5期76-80,共5页Modern Computer

基　　金：广东省科技计划项目(No.2012B010900089)

摘　　要：智能视频监控随着大数据视频分析技术的应用得到迅速发展,通过实时监控,视频分析系统即时反应,识别出视频监控采集到的目标人脸。在基于ARM11的S3C6410嵌入式硬件平台,以Linux操作系统为软件平台,用LBP算法对人脸图像进行预处理,减少光照对识别的干扰;用PCA算法对经一致模式统计后的均衡直方图进行特征提取和降维,降低数据的计算量;对降维后的数据运用岭回归算法进行分类,设计并优化LBP+PCA算法,结合Ridge Regression分类技术作为人脸识别视频分析的解决方案。Intelligent video surveillance system has been developing rapidly with the application of large data video analysis technology. Through re- al-time monitoring, real time analysis system of reaction, to identify the target face. The video analysis takes the ARMll processor as the hardware platform, uses ordinary camera as facial image capture device, 7-inch touch-screen LCD display as an input. Software based on embedded Linux as operating system, combined with LBP local binary pattern, PCA principal component analysis algorithm, Ridge Regression algorithm for face recognition algorithm solution, breaks through the problem face size, distance, light interference.

关 键 词：视频分析 LPB算法 PCA算法 岭回归算法 人脸识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]