一种人脸的检测与定位方法  

A Method for Face Detection and Location

作　　者：张永梅[1] 韩焱[1] 商细云[2] 

机构地区：[1]中北大学电子信息工程系,山西太原030051 [2]中北大学计算机科学与技术系,山西太原030051

出　　处：《中北大学学报（自然科学版）》2006年第3期229-233,共5页Journal of North University of China(Natural Science Edition)

基　　金：中北大学自然科学基金资助项目(200406)

摘　　要：提出一种基于肤色的人脸检测定位算法,设计了基于肤色的人脸检测和定位系统.采用了增强人脸特征与脸部皮肤之间对比度的方法以及二值化方法,改进了预处理的效果.使用了基于边界方法和基于区域方法相结合的算法,提取了眼睛、嘴和鼻子等关键特征,最终较好地实现了人脸定位.在M icrosoftW indow s M E平台上,利用V isua l C++6.0开发了软件.实验结果表明,该软件对于一定尺寸范围内清晰的正面人脸图像能够正确检测定位并提取特征.The detection and location of face is one of the important links in face recognition. In this paper, the authors have presented an algorithm and designed a system for face detection and location based on complexion. By strengthening the contrast between face features and facial complexion and by adopting binary image processing method, the system has improved the preprocessing effect; and by using boundary-based algorithm plus region-based algorithm, the system has realized face location through the extraction of the features of eyes, nose and mouth using. Taking advantages of Visual C＋＋ 6.0, the authors have also developed corresponding software based on Microsoft Windows ME. Experiment results prove that the system is valid in detecting, locating and extracting frontal-view face features in a certain range.

关 键 词：图像分割 人脸定位 肤色 人脸检测 特征提取 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]