一种基于肤色检测和Haar级联分类器的实时人脸检测系统  

A Real-time Face Detection System Based on Skin Detection and Haar Cascade Classifier

作　　者：王思霖 WANG Silin(School of Information Engineering,Xinyang Agriculture and Forestry University,Xinyang Henan 464000)

机构地区：[1]信阳农林学院信息工程学院,河南信阳464000

出　　处：《软件》2022年第7期125-127,共3页Software

摘　　要：人脸检测是一种在数字图像中找到人脸位置和大小的技术。常用于人脸识别、人脸追踪、面部动作捕捉、相机自动对焦等应用中。本文设计并实现了一种基于肤色检测和Haar级联分类器的系统来进行实时人脸检测,先通过肤色检测过滤掉图像中的非皮肤像素区域,后通过Haar级联分类器对剩余像素区域中的人脸进行检测。实验结果表明本系统能够实时地对视频画面中的人脸进行检测,且人脸检测算法计算时间明显小于传统的检测算法。Face detection is a technique for finding the position and size of faces in digital images.Commonly used in face recognition,face tracking,facial motion capture,camera auto focus and other applications.This paper designs and implements a system based on skin color detection and Haar cascade classifier for real-time face detection.Firstly,the non-skin pixels in the image are filtered out by skin detection,and then the Haar cascade classifier detect faces in the remaining pixels.The experimental results show that the system can detect the face in video in real time,and the consuming time of the face detection algorithm is significantly faster than that of the traditional detection algorithm.

关 键 词：人脸检测 肤色检测 Haar级联分类器 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]