基于OpenCV的视频人脸识别系统设计  

Design of Face Recognition System in Video Based on OpenCV

作　　者：余建波 Yu Jianbo(Traffic Police Detachment o f Xinyu Public Security Bureau,Jiangxi Province,JiangXi,XinYu,338000)

机构地区：[1]江西省新余市公安局交通警察支队,江西新余338000

出　　处：《信息通信》2018年第12期40-42,共3页Information & Communications

摘　　要：人脸识别属于生物特征识别,对于鉴别人物有着非常重要的作用,将人脸识别运用到视频监控中可以大大减少搜寻特定人物的工作量。在此背景下,以OpenCV库为基础,采用Qt工具开发了一套面向监控视频中的人脸识别系统。具体包括外部图像的获取、初步处理、人脸检测方法的设计。重点解决了图像灰度化、滤波、人脸识别环节中的噪声信息剔除等关键技术问题。经对系统的实验测试,结果表明文中提出的系统对于视频中的人脸识别着较高的检测速度和准确率。Face recognition is a kind of biometric recognition, which plays a very important role in the identification of people. The application of face recognition in video surveillance can greatly reduce the workload of searching for specific people. Under this background, a face recognition system for surveillance video is developed using QT tool based on OpenCV library. Including the acquisition of external images, preliminary processing, face detection method design. The key technical problems such as image grayscale, filtering, and noise elimination in face recognition are solved. The experimental results show that the proposed system has high detection speed and accuracy in face recognition in video.

关 键 词：人脸识别 OPENCV 视频 

分 类 号：TP309.3[自动化与计算机技术—计算机系统结构]